Prosodic Feature-Based Discriminatively Trained Low Resource Speech Recognition System

Speech recognition has been an active field of research in the last few decades since it facilitates better human–computer interaction. Native language automatic speech recognition (ASR) systems are still underdeveloped. Punjabi ASR systems are in their infancy stage because most research has been c...
Ausführliche Beschreibung

Gespeichert in:

Autor*in:	Taniya Hasija [verfasserIn] Virender Kadyan [verfasserIn] Kalpna Guleria [verfasserIn] Abdullah Alharbi [verfasserIn] Hashem Alyami [verfasserIn] Nitin Goyal [verfasserIn]

Format:	E-Artikel
Sprache:	Englisch

Erschienen:	2022

Schlagwörter:	children Punjabi ASR discriminative techniques feature extraction prosodic features data augmentation

Übergeordnetes Werk:	In: Sustainability - MDPI AG, 2009, 14(2022), 2, p 614
Übergeordnetes Werk:	volume:14 ; year:2022 ; number:2, p 614

Links:	Link aufrufen Link aufrufen Link aufrufen Journal toc

DOI / URN:	10.3390/su14020614

Katalog-ID:	DOAJ086025414

Internformat


LEADER	01000caa a22002652 4500
001	DOAJ086025414
003	DE-627
005	20240414210025.0
007	cr uuu---uuuuu
008	230311s2022 xx \|\|\|\|\|o 00\| \|\|eng c
024	7		\|a 10.3390/su14020614 \|2 doi
035			\|a (DE-627)DOAJ086025414
035			\|a (DE-599)DOAJ376015a885a4426684d795ece42beaac
040			\|a DE-627 \|b ger \|c DE-627 \|e rakwb
041			\|a eng
050		0	\|a TD194-195
050		0	\|a TJ807-830
050		0	\|a GE1-350
100	0		\|a Taniya Hasija \|e verfasserin \|4 aut
245	1	0	\|a Prosodic Feature-Based Discriminatively Trained Low Resource Speech Recognition System
264		1	\|c 2022
336			\|a Text \|b txt \|2 rdacontent
337			\|a Computermedien \|b c \|2 rdamedia
338			\|a Online-Ressource \|b cr \|2 rdacarrier
520			\|a Speech recognition has been an active field of research in the last few decades since it facilitates better human–computer interaction. Native language automatic speech recognition (ASR) systems are still underdeveloped. Punjabi ASR systems are in their infancy stage because most research has been conducted only on adult speech systems; however, less work has been performed on Punjabi children’s ASR systems. This research aimed to build a prosodic feature-based automatic children speech recognition system using discriminative modeling techniques. The corpus of Punjabi children’s speech has various runtime challenges, such as acoustic variations with varying speakers’ ages. Efforts were made to implement out-domain data augmentation to overcome such issues using Tacotron-based text to a speech synthesizer. The prosodic features were extracted from Punjabi children’s speech corpus, then particular prosodic features were coupled with Mel Frequency Cepstral Coefficient (MFCC) features before being submitted to an ASR framework. The system modeling process investigated various approaches, which included Maximum Mutual Information (MMI), Boosted Maximum Mutual Information (bMMI), and feature-based Maximum Mutual Information (fMMI). The out-domain data augmentation was performed to enhance the corpus. After that, prosodic features were also extracted from the extended corpus, and experiments were conducted on both individual and integrated prosodic-based acoustic features. It was observed that the fMMI technique exhibited 20% to 25% relative improvement in word error rate compared with MMI and bMMI techniques. Further, it was enhanced using an augmented dataset and hybrid front-end features (MFCC + POV + Fo + Voice quality) with a relative improvement of 13% compared with the earlier baseline system.
650		4	\|a children Punjabi ASR
650		4	\|a discriminative techniques
650		4	\|a feature extraction
650		4	\|a prosodic features
650		4	\|a data augmentation
653		0	\|a Environmental effects of industries and plants
653		0	\|a Renewable energy sources
653		0	\|a Environmental sciences
700	0		\|a Virender Kadyan \|e verfasserin \|4 aut
700	0		\|a Kalpna Guleria \|e verfasserin \|4 aut
700	0		\|a Abdullah Alharbi \|e verfasserin \|4 aut
700	0		\|a Hashem Alyami \|e verfasserin \|4 aut
700	0		\|a Nitin Goyal \|e verfasserin \|4 aut
773	0	8	\|i In \|t Sustainability \|d MDPI AG, 2009 \|g 14(2022), 2, p 614 \|w (DE-627)610604120 \|w (DE-600)2518383-7 \|x 20711050 \|7 nnns
773	1	8	\|g volume:14 \|g year:2022 \|g number:2, p 614
856	4	0	\|u https://doi.org/10.3390/su14020614 \|z kostenfrei
856	4	0	\|u https://doaj.org/article/376015a885a4426684d795ece42beaac \|z kostenfrei
856	4	0	\|u https://www.mdpi.com/2071-1050/14/2/614 \|z kostenfrei
856	4	2	\|u https://doaj.org/toc/2071-1050 \|y Journal toc \|z kostenfrei
912			\|a GBV_USEFLAG_A
912			\|a SYSFLAG_A
912			\|a GBV_DOAJ
912			\|a GBV_ILN_11
912			\|a GBV_ILN_20
912			\|a GBV_ILN_22
912			\|a GBV_ILN_23
912			\|a GBV_ILN_24
912			\|a GBV_ILN_31
912			\|a GBV_ILN_39
912			\|a GBV_ILN_40
912			\|a GBV_ILN_60
912			\|a GBV_ILN_62
912			\|a GBV_ILN_63
912			\|a GBV_ILN_65
912			\|a GBV_ILN_69
912			\|a GBV_ILN_70
912			\|a GBV_ILN_73
912			\|a GBV_ILN_95
912			\|a GBV_ILN_110
912			\|a GBV_ILN_151
912			\|a GBV_ILN_161
912			\|a GBV_ILN_170
912			\|a GBV_ILN_213
912			\|a GBV_ILN_224
912			\|a GBV_ILN_230
912			\|a GBV_ILN_285
912			\|a GBV_ILN_293
912			\|a GBV_ILN_370
912			\|a GBV_ILN_602
912			\|a GBV_ILN_2014
912			\|a GBV_ILN_2507
912			\|a GBV_ILN_4012
912			\|a GBV_ILN_4037
912			\|a GBV_ILN_4112
912			\|a GBV_ILN_4125
912			\|a GBV_ILN_4126
912			\|a GBV_ILN_4249
912			\|a GBV_ILN_4305
912			\|a GBV_ILN_4306
912			\|a GBV_ILN_4322
912			\|a GBV_ILN_4323
912			\|a GBV_ILN_4324
912			\|a GBV_ILN_4325
912			\|a GBV_ILN_4367
912			\|a GBV_ILN_4700
951			\|a AR
952			\|d 14 \|j 2022 \|e 2, p 614

Indexfelder

author_variant	t h th v k vk k g kg a a aa h a ha n g ng
matchkey_str	article:20711050:2022----::rsdcetrbsdiciiaieyrielweorep
hierarchy_sort_str	2022
callnumber-subject-code	TD
publishDate	2022
allfields	10.3390/su14020614 doi (DE-627)DOAJ086025414 (DE-599)DOAJ376015a885a4426684d795ece42beaac DE-627 ger DE-627 rakwb eng TD194-195 TJ807-830 GE1-350 Taniya Hasija verfasserin aut Prosodic Feature-Based Discriminatively Trained Low Resource Speech Recognition System 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Speech recognition has been an active field of research in the last few decades since it facilitates better human–computer interaction. Native language automatic speech recognition (ASR) systems are still underdeveloped. Punjabi ASR systems are in their infancy stage because most research has been conducted only on adult speech systems; however, less work has been performed on Punjabi children’s ASR systems. This research aimed to build a prosodic feature-based automatic children speech recognition system using discriminative modeling techniques. The corpus of Punjabi children’s speech has various runtime challenges, such as acoustic variations with varying speakers’ ages. Efforts were made to implement out-domain data augmentation to overcome such issues using Tacotron-based text to a speech synthesizer. The prosodic features were extracted from Punjabi children’s speech corpus, then particular prosodic features were coupled with Mel Frequency Cepstral Coefficient (MFCC) features before being submitted to an ASR framework. The system modeling process investigated various approaches, which included Maximum Mutual Information (MMI), Boosted Maximum Mutual Information (bMMI), and feature-based Maximum Mutual Information (fMMI). The out-domain data augmentation was performed to enhance the corpus. After that, prosodic features were also extracted from the extended corpus, and experiments were conducted on both individual and integrated prosodic-based acoustic features. It was observed that the fMMI technique exhibited 20% to 25% relative improvement in word error rate compared with MMI and bMMI techniques. Further, it was enhanced using an augmented dataset and hybrid front-end features (MFCC + POV + Fo + Voice quality) with a relative improvement of 13% compared with the earlier baseline system. children Punjabi ASR discriminative techniques feature extraction prosodic features data augmentation Environmental effects of industries and plants Renewable energy sources Environmental sciences Virender Kadyan verfasserin aut Kalpna Guleria verfasserin aut Abdullah Alharbi verfasserin aut Hashem Alyami verfasserin aut Nitin Goyal verfasserin aut In Sustainability MDPI AG, 2009 14(2022), 2, p 614 (DE-627)610604120 (DE-600)2518383-7 20711050 nnns volume:14 year:2022 number:2, p 614 https://doi.org/10.3390/su14020614 kostenfrei https://doaj.org/article/376015a885a4426684d795ece42beaac kostenfrei https://www.mdpi.com/2071-1050/14/2/614 kostenfrei https://doaj.org/toc/2071-1050 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2507 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4367 GBV_ILN_4700 AR 14 2022 2, p 614
spelling	10.3390/su14020614 doi (DE-627)DOAJ086025414 (DE-599)DOAJ376015a885a4426684d795ece42beaac DE-627 ger DE-627 rakwb eng TD194-195 TJ807-830 GE1-350 Taniya Hasija verfasserin aut Prosodic Feature-Based Discriminatively Trained Low Resource Speech Recognition System 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Speech recognition has been an active field of research in the last few decades since it facilitates better human–computer interaction. Native language automatic speech recognition (ASR) systems are still underdeveloped. Punjabi ASR systems are in their infancy stage because most research has been conducted only on adult speech systems; however, less work has been performed on Punjabi children’s ASR systems. This research aimed to build a prosodic feature-based automatic children speech recognition system using discriminative modeling techniques. The corpus of Punjabi children’s speech has various runtime challenges, such as acoustic variations with varying speakers’ ages. Efforts were made to implement out-domain data augmentation to overcome such issues using Tacotron-based text to a speech synthesizer. The prosodic features were extracted from Punjabi children’s speech corpus, then particular prosodic features were coupled with Mel Frequency Cepstral Coefficient (MFCC) features before being submitted to an ASR framework. The system modeling process investigated various approaches, which included Maximum Mutual Information (MMI), Boosted Maximum Mutual Information (bMMI), and feature-based Maximum Mutual Information (fMMI). The out-domain data augmentation was performed to enhance the corpus. After that, prosodic features were also extracted from the extended corpus, and experiments were conducted on both individual and integrated prosodic-based acoustic features. It was observed that the fMMI technique exhibited 20% to 25% relative improvement in word error rate compared with MMI and bMMI techniques. Further, it was enhanced using an augmented dataset and hybrid front-end features (MFCC + POV + Fo + Voice quality) with a relative improvement of 13% compared with the earlier baseline system. children Punjabi ASR discriminative techniques feature extraction prosodic features data augmentation Environmental effects of industries and plants Renewable energy sources Environmental sciences Virender Kadyan verfasserin aut Kalpna Guleria verfasserin aut Abdullah Alharbi verfasserin aut Hashem Alyami verfasserin aut Nitin Goyal verfasserin aut In Sustainability MDPI AG, 2009 14(2022), 2, p 614 (DE-627)610604120 (DE-600)2518383-7 20711050 nnns volume:14 year:2022 number:2, p 614 https://doi.org/10.3390/su14020614 kostenfrei https://doaj.org/article/376015a885a4426684d795ece42beaac kostenfrei https://www.mdpi.com/2071-1050/14/2/614 kostenfrei https://doaj.org/toc/2071-1050 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2507 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4367 GBV_ILN_4700 AR 14 2022 2, p 614
allfields_unstemmed	10.3390/su14020614 doi (DE-627)DOAJ086025414 (DE-599)DOAJ376015a885a4426684d795ece42beaac DE-627 ger DE-627 rakwb eng TD194-195 TJ807-830 GE1-350 Taniya Hasija verfasserin aut Prosodic Feature-Based Discriminatively Trained Low Resource Speech Recognition System 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Speech recognition has been an active field of research in the last few decades since it facilitates better human–computer interaction. Native language automatic speech recognition (ASR) systems are still underdeveloped. Punjabi ASR systems are in their infancy stage because most research has been conducted only on adult speech systems; however, less work has been performed on Punjabi children’s ASR systems. This research aimed to build a prosodic feature-based automatic children speech recognition system using discriminative modeling techniques. The corpus of Punjabi children’s speech has various runtime challenges, such as acoustic variations with varying speakers’ ages. Efforts were made to implement out-domain data augmentation to overcome such issues using Tacotron-based text to a speech synthesizer. The prosodic features were extracted from Punjabi children’s speech corpus, then particular prosodic features were coupled with Mel Frequency Cepstral Coefficient (MFCC) features before being submitted to an ASR framework. The system modeling process investigated various approaches, which included Maximum Mutual Information (MMI), Boosted Maximum Mutual Information (bMMI), and feature-based Maximum Mutual Information (fMMI). The out-domain data augmentation was performed to enhance the corpus. After that, prosodic features were also extracted from the extended corpus, and experiments were conducted on both individual and integrated prosodic-based acoustic features. It was observed that the fMMI technique exhibited 20% to 25% relative improvement in word error rate compared with MMI and bMMI techniques. Further, it was enhanced using an augmented dataset and hybrid front-end features (MFCC + POV + Fo + Voice quality) with a relative improvement of 13% compared with the earlier baseline system. children Punjabi ASR discriminative techniques feature extraction prosodic features data augmentation Environmental effects of industries and plants Renewable energy sources Environmental sciences Virender Kadyan verfasserin aut Kalpna Guleria verfasserin aut Abdullah Alharbi verfasserin aut Hashem Alyami verfasserin aut Nitin Goyal verfasserin aut In Sustainability MDPI AG, 2009 14(2022), 2, p 614 (DE-627)610604120 (DE-600)2518383-7 20711050 nnns volume:14 year:2022 number:2, p 614 https://doi.org/10.3390/su14020614 kostenfrei https://doaj.org/article/376015a885a4426684d795ece42beaac kostenfrei https://www.mdpi.com/2071-1050/14/2/614 kostenfrei https://doaj.org/toc/2071-1050 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2507 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4367 GBV_ILN_4700 AR 14 2022 2, p 614
allfieldsGer	10.3390/su14020614 doi (DE-627)DOAJ086025414 (DE-599)DOAJ376015a885a4426684d795ece42beaac DE-627 ger DE-627 rakwb eng TD194-195 TJ807-830 GE1-350 Taniya Hasija verfasserin aut Prosodic Feature-Based Discriminatively Trained Low Resource Speech Recognition System 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Speech recognition has been an active field of research in the last few decades since it facilitates better human–computer interaction. Native language automatic speech recognition (ASR) systems are still underdeveloped. Punjabi ASR systems are in their infancy stage because most research has been conducted only on adult speech systems; however, less work has been performed on Punjabi children’s ASR systems. This research aimed to build a prosodic feature-based automatic children speech recognition system using discriminative modeling techniques. The corpus of Punjabi children’s speech has various runtime challenges, such as acoustic variations with varying speakers’ ages. Efforts were made to implement out-domain data augmentation to overcome such issues using Tacotron-based text to a speech synthesizer. The prosodic features were extracted from Punjabi children’s speech corpus, then particular prosodic features were coupled with Mel Frequency Cepstral Coefficient (MFCC) features before being submitted to an ASR framework. The system modeling process investigated various approaches, which included Maximum Mutual Information (MMI), Boosted Maximum Mutual Information (bMMI), and feature-based Maximum Mutual Information (fMMI). The out-domain data augmentation was performed to enhance the corpus. After that, prosodic features were also extracted from the extended corpus, and experiments were conducted on both individual and integrated prosodic-based acoustic features. It was observed that the fMMI technique exhibited 20% to 25% relative improvement in word error rate compared with MMI and bMMI techniques. Further, it was enhanced using an augmented dataset and hybrid front-end features (MFCC + POV + Fo + Voice quality) with a relative improvement of 13% compared with the earlier baseline system. children Punjabi ASR discriminative techniques feature extraction prosodic features data augmentation Environmental effects of industries and plants Renewable energy sources Environmental sciences Virender Kadyan verfasserin aut Kalpna Guleria verfasserin aut Abdullah Alharbi verfasserin aut Hashem Alyami verfasserin aut Nitin Goyal verfasserin aut In Sustainability MDPI AG, 2009 14(2022), 2, p 614 (DE-627)610604120 (DE-600)2518383-7 20711050 nnns volume:14 year:2022 number:2, p 614 https://doi.org/10.3390/su14020614 kostenfrei https://doaj.org/article/376015a885a4426684d795ece42beaac kostenfrei https://www.mdpi.com/2071-1050/14/2/614 kostenfrei https://doaj.org/toc/2071-1050 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2507 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4367 GBV_ILN_4700 AR 14 2022 2, p 614
allfieldsSound	10.3390/su14020614 doi (DE-627)DOAJ086025414 (DE-599)DOAJ376015a885a4426684d795ece42beaac DE-627 ger DE-627 rakwb eng TD194-195 TJ807-830 GE1-350 Taniya Hasija verfasserin aut Prosodic Feature-Based Discriminatively Trained Low Resource Speech Recognition System 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Speech recognition has been an active field of research in the last few decades since it facilitates better human–computer interaction. Native language automatic speech recognition (ASR) systems are still underdeveloped. Punjabi ASR systems are in their infancy stage because most research has been conducted only on adult speech systems; however, less work has been performed on Punjabi children’s ASR systems. This research aimed to build a prosodic feature-based automatic children speech recognition system using discriminative modeling techniques. The corpus of Punjabi children’s speech has various runtime challenges, such as acoustic variations with varying speakers’ ages. Efforts were made to implement out-domain data augmentation to overcome such issues using Tacotron-based text to a speech synthesizer. The prosodic features were extracted from Punjabi children’s speech corpus, then particular prosodic features were coupled with Mel Frequency Cepstral Coefficient (MFCC) features before being submitted to an ASR framework. The system modeling process investigated various approaches, which included Maximum Mutual Information (MMI), Boosted Maximum Mutual Information (bMMI), and feature-based Maximum Mutual Information (fMMI). The out-domain data augmentation was performed to enhance the corpus. After that, prosodic features were also extracted from the extended corpus, and experiments were conducted on both individual and integrated prosodic-based acoustic features. It was observed that the fMMI technique exhibited 20% to 25% relative improvement in word error rate compared with MMI and bMMI techniques. Further, it was enhanced using an augmented dataset and hybrid front-end features (MFCC + POV + Fo + Voice quality) with a relative improvement of 13% compared with the earlier baseline system. children Punjabi ASR discriminative techniques feature extraction prosodic features data augmentation Environmental effects of industries and plants Renewable energy sources Environmental sciences Virender Kadyan verfasserin aut Kalpna Guleria verfasserin aut Abdullah Alharbi verfasserin aut Hashem Alyami verfasserin aut Nitin Goyal verfasserin aut In Sustainability MDPI AG, 2009 14(2022), 2, p 614 (DE-627)610604120 (DE-600)2518383-7 20711050 nnns volume:14 year:2022 number:2, p 614 https://doi.org/10.3390/su14020614 kostenfrei https://doaj.org/article/376015a885a4426684d795ece42beaac kostenfrei https://www.mdpi.com/2071-1050/14/2/614 kostenfrei https://doaj.org/toc/2071-1050 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2507 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4367 GBV_ILN_4700 AR 14 2022 2, p 614
language	English
source	In Sustainability 14(2022), 2, p 614 volume:14 year:2022 number:2, p 614
sourceStr	In Sustainability 14(2022), 2, p 614 volume:14 year:2022 number:2, p 614
format_phy_str_mv	Article
institution	findex.gbv.de
topic_facet	children Punjabi ASR discriminative techniques feature extraction prosodic features data augmentation Environmental effects of industries and plants Renewable energy sources Environmental sciences
isfreeaccess_bool	true
container_title	Sustainability
authorswithroles_txt_mv	Taniya Hasija @@aut@@ Virender Kadyan @@aut@@ Kalpna Guleria @@aut@@ Abdullah Alharbi @@aut@@ Hashem Alyami @@aut@@ Nitin Goyal @@aut@@
publishDateDaySort_date	2022-01-01T00:00:00Z
hierarchy_top_id	610604120
id	DOAJ086025414
language_de	englisch
fullrecord	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">DOAJ086025414</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240414210025.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230311s2022 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.3390/su14020614</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ086025414</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ376015a885a4426684d795ece42beaac</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">TD194-195</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">TJ807-830</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">GE1-350</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Taniya Hasija</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Prosodic Feature-Based Discriminatively Trained Low Resource Speech Recognition System</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Speech recognition has been an active field of research in the last few decades since it facilitates better human–computer interaction. Native language automatic speech recognition (ASR) systems are still underdeveloped. Punjabi ASR systems are in their infancy stage because most research has been conducted only on adult speech systems; however, less work has been performed on Punjabi children’s ASR systems. This research aimed to build a prosodic feature-based automatic children speech recognition system using discriminative modeling techniques. The corpus of Punjabi children’s speech has various runtime challenges, such as acoustic variations with varying speakers’ ages. Efforts were made to implement out-domain data augmentation to overcome such issues using Tacotron-based text to a speech synthesizer. The prosodic features were extracted from Punjabi children’s speech corpus, then particular prosodic features were coupled with Mel Frequency Cepstral Coefficient (MFCC) features before being submitted to an ASR framework. The system modeling process investigated various approaches, which included Maximum Mutual Information (MMI), Boosted Maximum Mutual Information (bMMI), and feature-based Maximum Mutual Information (fMMI). The out-domain data augmentation was performed to enhance the corpus. After that, prosodic features were also extracted from the extended corpus, and experiments were conducted on both individual and integrated prosodic-based acoustic features. It was observed that the fMMI technique exhibited 20% to 25% relative improvement in word error rate compared with MMI and bMMI techniques. Further, it was enhanced using an augmented dataset and hybrid front-end features (MFCC + POV + Fo + Voice quality) with a relative improvement of 13% compared with the earlier baseline system.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">children Punjabi ASR</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">discriminative techniques</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">feature extraction</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">prosodic features</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">data augmentation</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Environmental effects of industries and plants</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Renewable energy sources</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Environmental sciences</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Virender Kadyan</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Kalpna Guleria</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Abdullah Alharbi</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Hashem Alyami</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Nitin Goyal</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">Sustainability</subfield><subfield code="d">MDPI AG, 2009</subfield><subfield code="g">14(2022), 2, p 614</subfield><subfield code="w">(DE-627)610604120</subfield><subfield code="w">(DE-600)2518383-7</subfield><subfield code="x">20711050</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:14</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:2, p 614</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.3390/su14020614</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/376015a885a4426684d795ece42beaac</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.mdpi.com/2071-1050/14/2/614</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2071-1050</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_224</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2507</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">14</subfield><subfield code="j">2022</subfield><subfield code="e">2, p 614</subfield></datafield></record></collection>
callnumber-first	T - Technology
author	Taniya Hasija
spellingShingle	Taniya Hasija misc TD194-195 misc TJ807-830 misc GE1-350 misc children Punjabi ASR misc discriminative techniques misc feature extraction misc prosodic features misc data augmentation misc Environmental effects of industries and plants misc Renewable energy sources misc Environmental sciences Prosodic Feature-Based Discriminatively Trained Low Resource Speech Recognition System
authorStr	Taniya Hasija
ppnlink_with_tag_str_mv	@@773@@(DE-627)610604120
format	electronic Article
delete_txt_mv	keep
author_role	aut aut aut aut aut aut
collection	DOAJ
remote_str	true
callnumber-label	TD194-195
illustrated	Not Illustrated
issn	20711050
topic_title	TD194-195 TJ807-830 GE1-350 Prosodic Feature-Based Discriminatively Trained Low Resource Speech Recognition System children Punjabi ASR discriminative techniques feature extraction prosodic features data augmentation
topic	misc TD194-195 misc TJ807-830 misc GE1-350 misc children Punjabi ASR misc discriminative techniques misc feature extraction misc prosodic features misc data augmentation misc Environmental effects of industries and plants misc Renewable energy sources misc Environmental sciences
topic_unstemmed	misc TD194-195 misc TJ807-830 misc GE1-350 misc children Punjabi ASR misc discriminative techniques misc feature extraction misc prosodic features misc data augmentation misc Environmental effects of industries and plants misc Renewable energy sources misc Environmental sciences
topic_browse	misc TD194-195 misc TJ807-830 misc GE1-350 misc children Punjabi ASR misc discriminative techniques misc feature extraction misc prosodic features misc data augmentation misc Environmental effects of industries and plants misc Renewable energy sources misc Environmental sciences
format_facet	Elektronische Aufsätze Aufsätze Elektronische Ressource
format_main_str_mv	Text Zeitschrift/Artikel
carriertype_str_mv	cr
hierarchy_parent_title	Sustainability
hierarchy_parent_id	610604120
hierarchy_top_title	Sustainability
isfreeaccess_txt	true
familylinks_str_mv	(DE-627)610604120 (DE-600)2518383-7
title	Prosodic Feature-Based Discriminatively Trained Low Resource Speech Recognition System
ctrlnum	(DE-627)DOAJ086025414 (DE-599)DOAJ376015a885a4426684d795ece42beaac
title_full	Prosodic Feature-Based Discriminatively Trained Low Resource Speech Recognition System
author_sort	Taniya Hasija
journal	Sustainability
journalStr	Sustainability
callnumber-first-code	T
lang_code	eng
isOA_bool	true
recordtype	marc
publishDateSort	2022
contenttype_str_mv	txt
author_browse	Taniya Hasija Virender Kadyan Kalpna Guleria Abdullah Alharbi Hashem Alyami Nitin Goyal
container_volume	14
class	TD194-195 TJ807-830 GE1-350
format_se	Elektronische Aufsätze
author-letter	Taniya Hasija
doi_str_mv	10.3390/su14020614
author2-role	verfasserin
title_sort	prosodic feature-based discriminatively trained low resource speech recognition system
callnumber	TD194-195
title_auth	Prosodic Feature-Based Discriminatively Trained Low Resource Speech Recognition System
abstract	Speech recognition has been an active field of research in the last few decades since it facilitates better human–computer interaction. Native language automatic speech recognition (ASR) systems are still underdeveloped. Punjabi ASR systems are in their infancy stage because most research has been conducted only on adult speech systems; however, less work has been performed on Punjabi children’s ASR systems. This research aimed to build a prosodic feature-based automatic children speech recognition system using discriminative modeling techniques. The corpus of Punjabi children’s speech has various runtime challenges, such as acoustic variations with varying speakers’ ages. Efforts were made to implement out-domain data augmentation to overcome such issues using Tacotron-based text to a speech synthesizer. The prosodic features were extracted from Punjabi children’s speech corpus, then particular prosodic features were coupled with Mel Frequency Cepstral Coefficient (MFCC) features before being submitted to an ASR framework. The system modeling process investigated various approaches, which included Maximum Mutual Information (MMI), Boosted Maximum Mutual Information (bMMI), and feature-based Maximum Mutual Information (fMMI). The out-domain data augmentation was performed to enhance the corpus. After that, prosodic features were also extracted from the extended corpus, and experiments were conducted on both individual and integrated prosodic-based acoustic features. It was observed that the fMMI technique exhibited 20% to 25% relative improvement in word error rate compared with MMI and bMMI techniques. Further, it was enhanced using an augmented dataset and hybrid front-end features (MFCC + POV + Fo + Voice quality) with a relative improvement of 13% compared with the earlier baseline system.
abstractGer	Speech recognition has been an active field of research in the last few decades since it facilitates better human–computer interaction. Native language automatic speech recognition (ASR) systems are still underdeveloped. Punjabi ASR systems are in their infancy stage because most research has been conducted only on adult speech systems; however, less work has been performed on Punjabi children’s ASR systems. This research aimed to build a prosodic feature-based automatic children speech recognition system using discriminative modeling techniques. The corpus of Punjabi children’s speech has various runtime challenges, such as acoustic variations with varying speakers’ ages. Efforts were made to implement out-domain data augmentation to overcome such issues using Tacotron-based text to a speech synthesizer. The prosodic features were extracted from Punjabi children’s speech corpus, then particular prosodic features were coupled with Mel Frequency Cepstral Coefficient (MFCC) features before being submitted to an ASR framework. The system modeling process investigated various approaches, which included Maximum Mutual Information (MMI), Boosted Maximum Mutual Information (bMMI), and feature-based Maximum Mutual Information (fMMI). The out-domain data augmentation was performed to enhance the corpus. After that, prosodic features were also extracted from the extended corpus, and experiments were conducted on both individual and integrated prosodic-based acoustic features. It was observed that the fMMI technique exhibited 20% to 25% relative improvement in word error rate compared with MMI and bMMI techniques. Further, it was enhanced using an augmented dataset and hybrid front-end features (MFCC + POV + Fo + Voice quality) with a relative improvement of 13% compared with the earlier baseline system.
abstract_unstemmed	Speech recognition has been an active field of research in the last few decades since it facilitates better human–computer interaction. Native language automatic speech recognition (ASR) systems are still underdeveloped. Punjabi ASR systems are in their infancy stage because most research has been conducted only on adult speech systems; however, less work has been performed on Punjabi children’s ASR systems. This research aimed to build a prosodic feature-based automatic children speech recognition system using discriminative modeling techniques. The corpus of Punjabi children’s speech has various runtime challenges, such as acoustic variations with varying speakers’ ages. Efforts were made to implement out-domain data augmentation to overcome such issues using Tacotron-based text to a speech synthesizer. The prosodic features were extracted from Punjabi children’s speech corpus, then particular prosodic features were coupled with Mel Frequency Cepstral Coefficient (MFCC) features before being submitted to an ASR framework. The system modeling process investigated various approaches, which included Maximum Mutual Information (MMI), Boosted Maximum Mutual Information (bMMI), and feature-based Maximum Mutual Information (fMMI). The out-domain data augmentation was performed to enhance the corpus. After that, prosodic features were also extracted from the extended corpus, and experiments were conducted on both individual and integrated prosodic-based acoustic features. It was observed that the fMMI technique exhibited 20% to 25% relative improvement in word error rate compared with MMI and bMMI techniques. Further, it was enhanced using an augmented dataset and hybrid front-end features (MFCC + POV + Fo + Voice quality) with a relative improvement of 13% compared with the earlier baseline system.
collection_details	GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2507 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4367 GBV_ILN_4700
container_issue	2, p 614
title_short	Prosodic Feature-Based Discriminatively Trained Low Resource Speech Recognition System
url	https://doi.org/10.3390/su14020614 https://doaj.org/article/376015a885a4426684d795ece42beaac https://www.mdpi.com/2071-1050/14/2/614 https://doaj.org/toc/2071-1050
remote_bool	true
author2	Virender Kadyan Kalpna Guleria Abdullah Alharbi Hashem Alyami Nitin Goyal
author2Str	Virender Kadyan Kalpna Guleria Abdullah Alharbi Hashem Alyami Nitin Goyal
ppnlink	610604120
callnumber-subject	TD - Environmental Technology
mediatype_str_mv	c
isOA_txt	true
hochschulschrift_bool	false
doi_str	10.3390/su14020614
callnumber-a	TD194-195
up_date	2024-07-03T18:16:10.734Z
_version_	1803582775741120512
fullrecord_marcxml	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">DOAJ086025414</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240414210025.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230311s2022 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.3390/su14020614</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ086025414</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ376015a885a4426684d795ece42beaac</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">TD194-195</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">TJ807-830</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">GE1-350</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Taniya Hasija</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Prosodic Feature-Based Discriminatively Trained Low Resource Speech Recognition System</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Speech recognition has been an active field of research in the last few decades since it facilitates better human–computer interaction. Native language automatic speech recognition (ASR) systems are still underdeveloped. Punjabi ASR systems are in their infancy stage because most research has been conducted only on adult speech systems; however, less work has been performed on Punjabi children’s ASR systems. This research aimed to build a prosodic feature-based automatic children speech recognition system using discriminative modeling techniques. The corpus of Punjabi children’s speech has various runtime challenges, such as acoustic variations with varying speakers’ ages. Efforts were made to implement out-domain data augmentation to overcome such issues using Tacotron-based text to a speech synthesizer. The prosodic features were extracted from Punjabi children’s speech corpus, then particular prosodic features were coupled with Mel Frequency Cepstral Coefficient (MFCC) features before being submitted to an ASR framework. The system modeling process investigated various approaches, which included Maximum Mutual Information (MMI), Boosted Maximum Mutual Information (bMMI), and feature-based Maximum Mutual Information (fMMI). The out-domain data augmentation was performed to enhance the corpus. After that, prosodic features were also extracted from the extended corpus, and experiments were conducted on both individual and integrated prosodic-based acoustic features. It was observed that the fMMI technique exhibited 20% to 25% relative improvement in word error rate compared with MMI and bMMI techniques. Further, it was enhanced using an augmented dataset and hybrid front-end features (MFCC + POV + Fo + Voice quality) with a relative improvement of 13% compared with the earlier baseline system.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">children Punjabi ASR</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">discriminative techniques</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">feature extraction</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">prosodic features</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">data augmentation</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Environmental effects of industries and plants</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Renewable energy sources</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Environmental sciences</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Virender Kadyan</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Kalpna Guleria</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Abdullah Alharbi</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Hashem Alyami</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Nitin Goyal</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">Sustainability</subfield><subfield code="d">MDPI AG, 2009</subfield><subfield code="g">14(2022), 2, p 614</subfield><subfield code="w">(DE-627)610604120</subfield><subfield code="w">(DE-600)2518383-7</subfield><subfield code="x">20711050</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:14</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:2, p 614</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.3390/su14020614</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/376015a885a4426684d795ece42beaac</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.mdpi.com/2071-1050/14/2/614</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2071-1050</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_224</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2507</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">14</subfield><subfield code="j">2022</subfield><subfield code="e">2, p 614</subfield></datafield></record></collection>
score	7.400222

Nicht das Richtige dabei?

Schreiben Sie uns!

Prosodic Feature-Based Discriminatively Trained Low Resource Speech Recognition System

Nicht das Richtige dabei?

Zugang & Verfügbarkeit

Vorhandene Bände

Nicht das Richtige dabei?