Analyzing and Visualizing Deep Neural Networks for Speech Recognition with Saliency-Adjusted Neuron Activation Profiles

Deep Learning-based Automatic Speech Recognition (ASR) models are very successful, but hard to interpret. To gain a better understanding of how Artificial Neural Networks (ANNs) accomplish their tasks, several introspection methods have been proposed. However, established introspection techniques ar...
Ausführliche Beschreibung

Gespeichert in:

Autor*in:	Andreas Krug [verfasserIn] Maral Ebrahimzadeh [verfasserIn] Jost Alemann [verfasserIn] Jens Johannsmeier [verfasserIn] Sebastian Stober [verfasserIn]

Format:	E-Artikel
Sprache:	Englisch

Erschienen:	2021

Schlagwörter:	explainable AI visualization model introspection speech recognition convolutional neural networks

Übergeordnetes Werk:	In: Electronics - MDPI AG, 2013, 10(2021), 11, p 1350
Übergeordnetes Werk:	volume:10 ; year:2021 ; number:11, p 1350

Links:	Link aufrufen Link aufrufen Link aufrufen Journal toc

DOI / URN:	10.3390/electronics10111350

Katalog-ID:	DOAJ084750995

Internformat


LEADER	01000caa a22002652 4500
001	DOAJ084750995
003	DE-627
005	20240412175114.0
007	cr uuu---uuuuu
008	230311s2021 xx \|\|\|\|\|o 00\| \|\|eng c
024	7		\|a 10.3390/electronics10111350 \|2 doi
035			\|a (DE-627)DOAJ084750995
035			\|a (DE-599)DOAJ6f27a9dc5cca4788bfb9bab3fd4731e7
040			\|a DE-627 \|b ger \|c DE-627 \|e rakwb
041			\|a eng
050		0	\|a TK7800-8360
100	0		\|a Andreas Krug \|e verfasserin \|4 aut
245	1	0	\|a Analyzing and Visualizing Deep Neural Networks for Speech Recognition with Saliency-Adjusted Neuron Activation Profiles
264		1	\|c 2021
336			\|a Text \|b txt \|2 rdacontent
337			\|a Computermedien \|b c \|2 rdamedia
338			\|a Online-Ressource \|b cr \|2 rdacarrier
520			\|a Deep Learning-based Automatic Speech Recognition (ASR) models are very successful, but hard to interpret. To gain a better understanding of how Artificial Neural Networks (ANNs) accomplish their tasks, several introspection methods have been proposed. However, established introspection techniques are mostly designed for computer vision tasks and rely on the data being visually interpretable, which limits their usefulness for understanding speech recognition models. To overcome this limitation, we developed a novel neuroscience-inspired technique for visualizing and understanding ANNs, called Saliency-Adjusted Neuron Activation Profiles (SNAPs). SNAPs are a flexible framework to analyze and visualize Deep Neural Networks that does not depend on visually interpretable data. In this work, we demonstrate how to utilize SNAPs for understanding fully-convolutional ASR models. This includes visualizing acoustic concepts learned by the model and the comparative analysis of their representations in the model layers.
650		4	\|a explainable AI
650		4	\|a visualization
650		4	\|a model introspection
650		4	\|a speech recognition
650		4	\|a convolutional neural networks
653		0	\|a Electronics
700	0		\|a Maral Ebrahimzadeh \|e verfasserin \|4 aut
700	0		\|a Jost Alemann \|e verfasserin \|4 aut
700	0		\|a Jens Johannsmeier \|e verfasserin \|4 aut
700	0		\|a Sebastian Stober \|e verfasserin \|4 aut
773	0	8	\|i In \|t Electronics \|d MDPI AG, 2013 \|g 10(2021), 11, p 1350 \|w (DE-627)718626478 \|w (DE-600)2662127-7 \|x 20799292 \|7 nnns
773	1	8	\|g volume:10 \|g year:2021 \|g number:11, p 1350
856	4	0	\|u https://doi.org/10.3390/electronics10111350 \|z kostenfrei
856	4	0	\|u https://doaj.org/article/6f27a9dc5cca4788bfb9bab3fd4731e7 \|z kostenfrei
856	4	0	\|u https://www.mdpi.com/2079-9292/10/11/1350 \|z kostenfrei
856	4	2	\|u https://doaj.org/toc/2079-9292 \|y Journal toc \|z kostenfrei
912			\|a GBV_USEFLAG_A
912			\|a SYSFLAG_A
912			\|a GBV_DOAJ
912			\|a GBV_ILN_20
912			\|a GBV_ILN_22
912			\|a GBV_ILN_23
912			\|a GBV_ILN_24
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_105
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_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_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_4307
912			\|a GBV_ILN_4313
912			\|a GBV_ILN_4322
912			\|a GBV_ILN_4323
912			\|a GBV_ILN_4324
912			\|a GBV_ILN_4325
912			\|a GBV_ILN_4335
912			\|a GBV_ILN_4338
912			\|a GBV_ILN_4367
912			\|a GBV_ILN_4700
951			\|a AR
952			\|d 10 \|j 2021 \|e 11, p 1350

Indexfelder

author_variant	a k ak m e me j a ja j j jj s s ss
matchkey_str	article:20799292:2021----::nlznadiulzndenuantokfrpeheontowtslecajs
hierarchy_sort_str	2021
callnumber-subject-code	TK
publishDate	2021
allfields	10.3390/electronics10111350 doi (DE-627)DOAJ084750995 (DE-599)DOAJ6f27a9dc5cca4788bfb9bab3fd4731e7 DE-627 ger DE-627 rakwb eng TK7800-8360 Andreas Krug verfasserin aut Analyzing and Visualizing Deep Neural Networks for Speech Recognition with Saliency-Adjusted Neuron Activation Profiles 2021 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Deep Learning-based Automatic Speech Recognition (ASR) models are very successful, but hard to interpret. To gain a better understanding of how Artificial Neural Networks (ANNs) accomplish their tasks, several introspection methods have been proposed. However, established introspection techniques are mostly designed for computer vision tasks and rely on the data being visually interpretable, which limits their usefulness for understanding speech recognition models. To overcome this limitation, we developed a novel neuroscience-inspired technique for visualizing and understanding ANNs, called Saliency-Adjusted Neuron Activation Profiles (SNAPs). SNAPs are a flexible framework to analyze and visualize Deep Neural Networks that does not depend on visually interpretable data. In this work, we demonstrate how to utilize SNAPs for understanding fully-convolutional ASR models. This includes visualizing acoustic concepts learned by the model and the comparative analysis of their representations in the model layers. explainable AI visualization model introspection speech recognition convolutional neural networks Electronics Maral Ebrahimzadeh verfasserin aut Jost Alemann verfasserin aut Jens Johannsmeier verfasserin aut Sebastian Stober verfasserin aut In Electronics MDPI AG, 2013 10(2021), 11, p 1350 (DE-627)718626478 (DE-600)2662127-7 20799292 nnns volume:10 year:2021 number:11, p 1350 https://doi.org/10.3390/electronics10111350 kostenfrei https://doaj.org/article/6f27a9dc5cca4788bfb9bab3fd4731e7 kostenfrei https://www.mdpi.com/2079-9292/10/11/1350 kostenfrei https://doaj.org/toc/2079-9292 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 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_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 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_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 10 2021 11, p 1350
spelling	10.3390/electronics10111350 doi (DE-627)DOAJ084750995 (DE-599)DOAJ6f27a9dc5cca4788bfb9bab3fd4731e7 DE-627 ger DE-627 rakwb eng TK7800-8360 Andreas Krug verfasserin aut Analyzing and Visualizing Deep Neural Networks for Speech Recognition with Saliency-Adjusted Neuron Activation Profiles 2021 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Deep Learning-based Automatic Speech Recognition (ASR) models are very successful, but hard to interpret. To gain a better understanding of how Artificial Neural Networks (ANNs) accomplish their tasks, several introspection methods have been proposed. However, established introspection techniques are mostly designed for computer vision tasks and rely on the data being visually interpretable, which limits their usefulness for understanding speech recognition models. To overcome this limitation, we developed a novel neuroscience-inspired technique for visualizing and understanding ANNs, called Saliency-Adjusted Neuron Activation Profiles (SNAPs). SNAPs are a flexible framework to analyze and visualize Deep Neural Networks that does not depend on visually interpretable data. In this work, we demonstrate how to utilize SNAPs for understanding fully-convolutional ASR models. This includes visualizing acoustic concepts learned by the model and the comparative analysis of their representations in the model layers. explainable AI visualization model introspection speech recognition convolutional neural networks Electronics Maral Ebrahimzadeh verfasserin aut Jost Alemann verfasserin aut Jens Johannsmeier verfasserin aut Sebastian Stober verfasserin aut In Electronics MDPI AG, 2013 10(2021), 11, p 1350 (DE-627)718626478 (DE-600)2662127-7 20799292 nnns volume:10 year:2021 number:11, p 1350 https://doi.org/10.3390/electronics10111350 kostenfrei https://doaj.org/article/6f27a9dc5cca4788bfb9bab3fd4731e7 kostenfrei https://www.mdpi.com/2079-9292/10/11/1350 kostenfrei https://doaj.org/toc/2079-9292 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 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_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 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_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 10 2021 11, p 1350
allfields_unstemmed	10.3390/electronics10111350 doi (DE-627)DOAJ084750995 (DE-599)DOAJ6f27a9dc5cca4788bfb9bab3fd4731e7 DE-627 ger DE-627 rakwb eng TK7800-8360 Andreas Krug verfasserin aut Analyzing and Visualizing Deep Neural Networks for Speech Recognition with Saliency-Adjusted Neuron Activation Profiles 2021 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Deep Learning-based Automatic Speech Recognition (ASR) models are very successful, but hard to interpret. To gain a better understanding of how Artificial Neural Networks (ANNs) accomplish their tasks, several introspection methods have been proposed. However, established introspection techniques are mostly designed for computer vision tasks and rely on the data being visually interpretable, which limits their usefulness for understanding speech recognition models. To overcome this limitation, we developed a novel neuroscience-inspired technique for visualizing and understanding ANNs, called Saliency-Adjusted Neuron Activation Profiles (SNAPs). SNAPs are a flexible framework to analyze and visualize Deep Neural Networks that does not depend on visually interpretable data. In this work, we demonstrate how to utilize SNAPs for understanding fully-convolutional ASR models. This includes visualizing acoustic concepts learned by the model and the comparative analysis of their representations in the model layers. explainable AI visualization model introspection speech recognition convolutional neural networks Electronics Maral Ebrahimzadeh verfasserin aut Jost Alemann verfasserin aut Jens Johannsmeier verfasserin aut Sebastian Stober verfasserin aut In Electronics MDPI AG, 2013 10(2021), 11, p 1350 (DE-627)718626478 (DE-600)2662127-7 20799292 nnns volume:10 year:2021 number:11, p 1350 https://doi.org/10.3390/electronics10111350 kostenfrei https://doaj.org/article/6f27a9dc5cca4788bfb9bab3fd4731e7 kostenfrei https://www.mdpi.com/2079-9292/10/11/1350 kostenfrei https://doaj.org/toc/2079-9292 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 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_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 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_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 10 2021 11, p 1350
allfieldsGer	10.3390/electronics10111350 doi (DE-627)DOAJ084750995 (DE-599)DOAJ6f27a9dc5cca4788bfb9bab3fd4731e7 DE-627 ger DE-627 rakwb eng TK7800-8360 Andreas Krug verfasserin aut Analyzing and Visualizing Deep Neural Networks for Speech Recognition with Saliency-Adjusted Neuron Activation Profiles 2021 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Deep Learning-based Automatic Speech Recognition (ASR) models are very successful, but hard to interpret. To gain a better understanding of how Artificial Neural Networks (ANNs) accomplish their tasks, several introspection methods have been proposed. However, established introspection techniques are mostly designed for computer vision tasks and rely on the data being visually interpretable, which limits their usefulness for understanding speech recognition models. To overcome this limitation, we developed a novel neuroscience-inspired technique for visualizing and understanding ANNs, called Saliency-Adjusted Neuron Activation Profiles (SNAPs). SNAPs are a flexible framework to analyze and visualize Deep Neural Networks that does not depend on visually interpretable data. In this work, we demonstrate how to utilize SNAPs for understanding fully-convolutional ASR models. This includes visualizing acoustic concepts learned by the model and the comparative analysis of their representations in the model layers. explainable AI visualization model introspection speech recognition convolutional neural networks Electronics Maral Ebrahimzadeh verfasserin aut Jost Alemann verfasserin aut Jens Johannsmeier verfasserin aut Sebastian Stober verfasserin aut In Electronics MDPI AG, 2013 10(2021), 11, p 1350 (DE-627)718626478 (DE-600)2662127-7 20799292 nnns volume:10 year:2021 number:11, p 1350 https://doi.org/10.3390/electronics10111350 kostenfrei https://doaj.org/article/6f27a9dc5cca4788bfb9bab3fd4731e7 kostenfrei https://www.mdpi.com/2079-9292/10/11/1350 kostenfrei https://doaj.org/toc/2079-9292 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 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_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 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_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 10 2021 11, p 1350
allfieldsSound	10.3390/electronics10111350 doi (DE-627)DOAJ084750995 (DE-599)DOAJ6f27a9dc5cca4788bfb9bab3fd4731e7 DE-627 ger DE-627 rakwb eng TK7800-8360 Andreas Krug verfasserin aut Analyzing and Visualizing Deep Neural Networks for Speech Recognition with Saliency-Adjusted Neuron Activation Profiles 2021 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Deep Learning-based Automatic Speech Recognition (ASR) models are very successful, but hard to interpret. To gain a better understanding of how Artificial Neural Networks (ANNs) accomplish their tasks, several introspection methods have been proposed. However, established introspection techniques are mostly designed for computer vision tasks and rely on the data being visually interpretable, which limits their usefulness for understanding speech recognition models. To overcome this limitation, we developed a novel neuroscience-inspired technique for visualizing and understanding ANNs, called Saliency-Adjusted Neuron Activation Profiles (SNAPs). SNAPs are a flexible framework to analyze and visualize Deep Neural Networks that does not depend on visually interpretable data. In this work, we demonstrate how to utilize SNAPs for understanding fully-convolutional ASR models. This includes visualizing acoustic concepts learned by the model and the comparative analysis of their representations in the model layers. explainable AI visualization model introspection speech recognition convolutional neural networks Electronics Maral Ebrahimzadeh verfasserin aut Jost Alemann verfasserin aut Jens Johannsmeier verfasserin aut Sebastian Stober verfasserin aut In Electronics MDPI AG, 2013 10(2021), 11, p 1350 (DE-627)718626478 (DE-600)2662127-7 20799292 nnns volume:10 year:2021 number:11, p 1350 https://doi.org/10.3390/electronics10111350 kostenfrei https://doaj.org/article/6f27a9dc5cca4788bfb9bab3fd4731e7 kostenfrei https://www.mdpi.com/2079-9292/10/11/1350 kostenfrei https://doaj.org/toc/2079-9292 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 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_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 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_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 10 2021 11, p 1350
language	English
source	In Electronics 10(2021), 11, p 1350 volume:10 year:2021 number:11, p 1350
sourceStr	In Electronics 10(2021), 11, p 1350 volume:10 year:2021 number:11, p 1350
format_phy_str_mv	Article
institution	findex.gbv.de
topic_facet	explainable AI visualization model introspection speech recognition convolutional neural networks Electronics
isfreeaccess_bool	true
container_title	Electronics
authorswithroles_txt_mv	Andreas Krug @@aut@@ Maral Ebrahimzadeh @@aut@@ Jost Alemann @@aut@@ Jens Johannsmeier @@aut@@ Sebastian Stober @@aut@@
publishDateDaySort_date	2021-01-01T00:00:00Z
hierarchy_top_id	718626478
id	DOAJ084750995
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">DOAJ084750995</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240412175114.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230311s2021 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.3390/electronics10111350</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ084750995</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ6f27a9dc5cca4788bfb9bab3fd4731e7</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">TK7800-8360</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Andreas Krug</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Analyzing and Visualizing Deep Neural Networks for Speech Recognition with Saliency-Adjusted Neuron Activation Profiles</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021</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">Deep Learning-based Automatic Speech Recognition (ASR) models are very successful, but hard to interpret. To gain a better understanding of how Artificial Neural Networks (ANNs) accomplish their tasks, several introspection methods have been proposed. However, established introspection techniques are mostly designed for computer vision tasks and rely on the data being visually interpretable, which limits their usefulness for understanding speech recognition models. To overcome this limitation, we developed a novel neuroscience-inspired technique for visualizing and understanding ANNs, called Saliency-Adjusted Neuron Activation Profiles (SNAPs). SNAPs are a flexible framework to analyze and visualize Deep Neural Networks that does not depend on visually interpretable data. In this work, we demonstrate how to utilize SNAPs for understanding fully-convolutional ASR models. This includes visualizing acoustic concepts learned by the model and the comparative analysis of their representations in the model layers.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">explainable AI</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">visualization</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">model introspection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">speech recognition</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">convolutional neural networks</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Electronics</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Maral Ebrahimzadeh</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Jost Alemann</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Jens Johannsmeier</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Sebastian Stober</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">Electronics</subfield><subfield code="d">MDPI AG, 2013</subfield><subfield code="g">10(2021), 11, p 1350</subfield><subfield code="w">(DE-627)718626478</subfield><subfield code="w">(DE-600)2662127-7</subfield><subfield code="x">20799292</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:10</subfield><subfield code="g">year:2021</subfield><subfield code="g">number:11, p 1350</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.3390/electronics10111350</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/6f27a9dc5cca4788bfb9bab3fd4731e7</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.mdpi.com/2079-9292/10/11/1350</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2079-9292</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_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_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_105</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_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_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_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</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_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</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">10</subfield><subfield code="j">2021</subfield><subfield code="e">11, p 1350</subfield></datafield></record></collection>
callnumber-first	T - Technology
author	Andreas Krug
spellingShingle	Andreas Krug misc TK7800-8360 misc explainable AI misc visualization misc model introspection misc speech recognition misc convolutional neural networks misc Electronics Analyzing and Visualizing Deep Neural Networks for Speech Recognition with Saliency-Adjusted Neuron Activation Profiles
authorStr	Andreas Krug
ppnlink_with_tag_str_mv	@@773@@(DE-627)718626478
format	electronic Article
delete_txt_mv	keep
author_role	aut aut aut aut aut
collection	DOAJ
remote_str	true
callnumber-label	TK7800-8360
illustrated	Not Illustrated
issn	20799292
topic_title	TK7800-8360 Analyzing and Visualizing Deep Neural Networks for Speech Recognition with Saliency-Adjusted Neuron Activation Profiles explainable AI visualization model introspection speech recognition convolutional neural networks
topic	misc TK7800-8360 misc explainable AI misc visualization misc model introspection misc speech recognition misc convolutional neural networks misc Electronics
topic_unstemmed	misc TK7800-8360 misc explainable AI misc visualization misc model introspection misc speech recognition misc convolutional neural networks misc Electronics
topic_browse	misc TK7800-8360 misc explainable AI misc visualization misc model introspection misc speech recognition misc convolutional neural networks misc Electronics
format_facet	Elektronische Aufsätze Aufsätze Elektronische Ressource
format_main_str_mv	Text Zeitschrift/Artikel
carriertype_str_mv	cr
hierarchy_parent_title	Electronics
hierarchy_parent_id	718626478
hierarchy_top_title	Electronics
isfreeaccess_txt	true
familylinks_str_mv	(DE-627)718626478 (DE-600)2662127-7
title	Analyzing and Visualizing Deep Neural Networks for Speech Recognition with Saliency-Adjusted Neuron Activation Profiles
ctrlnum	(DE-627)DOAJ084750995 (DE-599)DOAJ6f27a9dc5cca4788bfb9bab3fd4731e7
title_full	Analyzing and Visualizing Deep Neural Networks for Speech Recognition with Saliency-Adjusted Neuron Activation Profiles
author_sort	Andreas Krug
journal	Electronics
journalStr	Electronics
callnumber-first-code	T
lang_code	eng
isOA_bool	true
recordtype	marc
publishDateSort	2021
contenttype_str_mv	txt
author_browse	Andreas Krug Maral Ebrahimzadeh Jost Alemann Jens Johannsmeier Sebastian Stober
container_volume	10
class	TK7800-8360
format_se	Elektronische Aufsätze
author-letter	Andreas Krug
doi_str_mv	10.3390/electronics10111350
author2-role	verfasserin
title_sort	analyzing and visualizing deep neural networks for speech recognition with saliency-adjusted neuron activation profiles
callnumber	TK7800-8360
title_auth	Analyzing and Visualizing Deep Neural Networks for Speech Recognition with Saliency-Adjusted Neuron Activation Profiles
abstract	Deep Learning-based Automatic Speech Recognition (ASR) models are very successful, but hard to interpret. To gain a better understanding of how Artificial Neural Networks (ANNs) accomplish their tasks, several introspection methods have been proposed. However, established introspection techniques are mostly designed for computer vision tasks and rely on the data being visually interpretable, which limits their usefulness for understanding speech recognition models. To overcome this limitation, we developed a novel neuroscience-inspired technique for visualizing and understanding ANNs, called Saliency-Adjusted Neuron Activation Profiles (SNAPs). SNAPs are a flexible framework to analyze and visualize Deep Neural Networks that does not depend on visually interpretable data. In this work, we demonstrate how to utilize SNAPs for understanding fully-convolutional ASR models. This includes visualizing acoustic concepts learned by the model and the comparative analysis of their representations in the model layers.
abstractGer	Deep Learning-based Automatic Speech Recognition (ASR) models are very successful, but hard to interpret. To gain a better understanding of how Artificial Neural Networks (ANNs) accomplish their tasks, several introspection methods have been proposed. However, established introspection techniques are mostly designed for computer vision tasks and rely on the data being visually interpretable, which limits their usefulness for understanding speech recognition models. To overcome this limitation, we developed a novel neuroscience-inspired technique for visualizing and understanding ANNs, called Saliency-Adjusted Neuron Activation Profiles (SNAPs). SNAPs are a flexible framework to analyze and visualize Deep Neural Networks that does not depend on visually interpretable data. In this work, we demonstrate how to utilize SNAPs for understanding fully-convolutional ASR models. This includes visualizing acoustic concepts learned by the model and the comparative analysis of their representations in the model layers.
abstract_unstemmed	Deep Learning-based Automatic Speech Recognition (ASR) models are very successful, but hard to interpret. To gain a better understanding of how Artificial Neural Networks (ANNs) accomplish their tasks, several introspection methods have been proposed. However, established introspection techniques are mostly designed for computer vision tasks and rely on the data being visually interpretable, which limits their usefulness for understanding speech recognition models. To overcome this limitation, we developed a novel neuroscience-inspired technique for visualizing and understanding ANNs, called Saliency-Adjusted Neuron Activation Profiles (SNAPs). SNAPs are a flexible framework to analyze and visualize Deep Neural Networks that does not depend on visually interpretable data. In this work, we demonstrate how to utilize SNAPs for understanding fully-convolutional ASR models. This includes visualizing acoustic concepts learned by the model and the comparative analysis of their representations in the model layers.
collection_details	GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 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_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 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_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700
container_issue	11, p 1350
title_short	Analyzing and Visualizing Deep Neural Networks for Speech Recognition with Saliency-Adjusted Neuron Activation Profiles
url	https://doi.org/10.3390/electronics10111350 https://doaj.org/article/6f27a9dc5cca4788bfb9bab3fd4731e7 https://www.mdpi.com/2079-9292/10/11/1350 https://doaj.org/toc/2079-9292
remote_bool	true
author2	Maral Ebrahimzadeh Jost Alemann Jens Johannsmeier Sebastian Stober
author2Str	Maral Ebrahimzadeh Jost Alemann Jens Johannsmeier Sebastian Stober
ppnlink	718626478
callnumber-subject	TK - Electrical and Nuclear Engineering
mediatype_str_mv	c
isOA_txt	true
hochschulschrift_bool	false
doi_str	10.3390/electronics10111350
callnumber-a	TK7800-8360
up_date	2024-07-04T00:23:08.577Z
_version_	1803605863121813504
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">DOAJ084750995</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240412175114.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230311s2021 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.3390/electronics10111350</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ084750995</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ6f27a9dc5cca4788bfb9bab3fd4731e7</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">TK7800-8360</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Andreas Krug</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Analyzing and Visualizing Deep Neural Networks for Speech Recognition with Saliency-Adjusted Neuron Activation Profiles</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021</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">Deep Learning-based Automatic Speech Recognition (ASR) models are very successful, but hard to interpret. To gain a better understanding of how Artificial Neural Networks (ANNs) accomplish their tasks, several introspection methods have been proposed. However, established introspection techniques are mostly designed for computer vision tasks and rely on the data being visually interpretable, which limits their usefulness for understanding speech recognition models. To overcome this limitation, we developed a novel neuroscience-inspired technique for visualizing and understanding ANNs, called Saliency-Adjusted Neuron Activation Profiles (SNAPs). SNAPs are a flexible framework to analyze and visualize Deep Neural Networks that does not depend on visually interpretable data. In this work, we demonstrate how to utilize SNAPs for understanding fully-convolutional ASR models. This includes visualizing acoustic concepts learned by the model and the comparative analysis of their representations in the model layers.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">explainable AI</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">visualization</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">model introspection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">speech recognition</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">convolutional neural networks</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Electronics</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Maral Ebrahimzadeh</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Jost Alemann</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Jens Johannsmeier</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Sebastian Stober</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">Electronics</subfield><subfield code="d">MDPI AG, 2013</subfield><subfield code="g">10(2021), 11, p 1350</subfield><subfield code="w">(DE-627)718626478</subfield><subfield code="w">(DE-600)2662127-7</subfield><subfield code="x">20799292</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:10</subfield><subfield code="g">year:2021</subfield><subfield code="g">number:11, p 1350</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.3390/electronics10111350</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/6f27a9dc5cca4788bfb9bab3fd4731e7</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.mdpi.com/2079-9292/10/11/1350</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2079-9292</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_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_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_105</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_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_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_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</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_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</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">10</subfield><subfield code="j">2021</subfield><subfield code="e">11, p 1350</subfield></datafield></record></collection>
score	7.3997526

Nicht das Richtige dabei?

Schreiben Sie uns!

Analyzing and Visualizing Deep Neural Networks for Speech Recognition with Saliency-Adjusted Neuron Activation Profiles

Nicht das Richtige dabei?

Zugang & Verfügbarkeit

Vorhandene Bände

Nicht das Richtige dabei?