A Semi-Continuous State-Transition Probability HMM-Based Voice Activity Detector
<p/< <p<We introduce an efficient hidden Markov model-based voice activity detection (VAD) algorithm with time-variant state-transition probabilities in the underlying Markov chain. The transition probabilities vary in an exponential charge/discharge scheme and are softly merged with sta...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Othman H [verfasserIn] Aboulnasr T [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2007 |
|---|
| Übergeordnetes Werk: |
In: EURASIP Journal on Audio, Speech, and Music Processing ; (2007), 1, p 043218 year:2007 ; number:1, p 043218 |
|---|
| Links: |
|---|
| Katalog-ID: |
DOAJ066318912 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | DOAJ066318912 | ||
| 003 | DE-627 | ||
| 005 | 20230309055916.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 230228s2007 xx |||||o 00| ||eng c | ||
| 035 | |a (DE-627)DOAJ066318912 | ||
| 035 | |a (DE-599)DOAJ0081f53b410f4e7f8c6dc7b048846763 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 050 | 0 | |a QC221-246 | |
| 050 | 0 | |a QA75.5-76.95 | |
| 100 | 0 | |a Othman H |e verfasserin |4 aut | |
| 245 | 1 | 2 | |a A Semi-Continuous State-Transition Probability HMM-Based Voice Activity Detector |
| 264 | 1 | |c 2007 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 520 | |a <p/< <p<We introduce an efficient hidden Markov model-based voice activity detection (VAD) algorithm with time-variant state-transition probabilities in the underlying Markov chain. The transition probabilities vary in an exponential charge/discharge scheme and are softly merged with state conditional likelihood into a final VAD decision. Working in the domain of ITU-T G.729 parameters, with no additional cost for feature extraction, the proposed algorithm significantly outperforms G.729 Annex B VAD while providing a balanced tradeoff between clipping and false detection errors. The performance compares very favorably with the adaptive multirate VAD, option 2 (AMR2).</p< | ||
| 653 | 0 | |a Acoustics. Sound | |
| 653 | 0 | |a Electronic computers. Computer science | |
| 700 | 0 | |a Aboulnasr T |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i In |t EURASIP Journal on Audio, Speech, and Music Processing |g (2007), 1, p 043218 |
| 773 | 1 | 8 | |g year:2007 |g number:1, p 043218 |
| 856 | 4 | 0 | |u https://doaj.org/article/0081f53b410f4e7f8c6dc7b048846763 |z kostenfrei |
| 856 | 4 | 0 | |u http://asmp.eurasipjournals.com/content/2007/043218 |z kostenfrei |
| 856 | 4 | 2 | |u https://doaj.org/toc/1687-4714 |y Journal toc |z kostenfrei |
| 856 | 4 | 2 | |u https://doaj.org/toc/1687-4722 |y Journal toc |z kostenfrei |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_DOAJ | ||
| 951 | |a AR | ||
| 952 | |j 2007 |e 1, p 043218 | ||
| author_variant |
o h oh a t at |
|---|---|
| matchkey_str |
othmanhaboulnasrt:2007----:smcniuusaerniinrbblthmaev |
| hierarchy_sort_str |
2007 |
| callnumber-subject-code |
QC |
| publishDate |
2007 |
| allfields |
(DE-627)DOAJ066318912 (DE-599)DOAJ0081f53b410f4e7f8c6dc7b048846763 DE-627 ger DE-627 rakwb eng QC221-246 QA75.5-76.95 Othman H verfasserin aut A Semi-Continuous State-Transition Probability HMM-Based Voice Activity Detector 2007 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier <p/< <p<We introduce an efficient hidden Markov model-based voice activity detection (VAD) algorithm with time-variant state-transition probabilities in the underlying Markov chain. The transition probabilities vary in an exponential charge/discharge scheme and are softly merged with state conditional likelihood into a final VAD decision. Working in the domain of ITU-T G.729 parameters, with no additional cost for feature extraction, the proposed algorithm significantly outperforms G.729 Annex B VAD while providing a balanced tradeoff between clipping and false detection errors. The performance compares very favorably with the adaptive multirate VAD, option 2 (AMR2).</p< Acoustics. Sound Electronic computers. Computer science Aboulnasr T verfasserin aut In EURASIP Journal on Audio, Speech, and Music Processing (2007), 1, p 043218 year:2007 number:1, p 043218 https://doaj.org/article/0081f53b410f4e7f8c6dc7b048846763 kostenfrei http://asmp.eurasipjournals.com/content/2007/043218 kostenfrei https://doaj.org/toc/1687-4714 Journal toc kostenfrei https://doaj.org/toc/1687-4722 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ AR 2007 1, p 043218 |
| spelling |
(DE-627)DOAJ066318912 (DE-599)DOAJ0081f53b410f4e7f8c6dc7b048846763 DE-627 ger DE-627 rakwb eng QC221-246 QA75.5-76.95 Othman H verfasserin aut A Semi-Continuous State-Transition Probability HMM-Based Voice Activity Detector 2007 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier <p/< <p<We introduce an efficient hidden Markov model-based voice activity detection (VAD) algorithm with time-variant state-transition probabilities in the underlying Markov chain. The transition probabilities vary in an exponential charge/discharge scheme and are softly merged with state conditional likelihood into a final VAD decision. Working in the domain of ITU-T G.729 parameters, with no additional cost for feature extraction, the proposed algorithm significantly outperforms G.729 Annex B VAD while providing a balanced tradeoff between clipping and false detection errors. The performance compares very favorably with the adaptive multirate VAD, option 2 (AMR2).</p< Acoustics. Sound Electronic computers. Computer science Aboulnasr T verfasserin aut In EURASIP Journal on Audio, Speech, and Music Processing (2007), 1, p 043218 year:2007 number:1, p 043218 https://doaj.org/article/0081f53b410f4e7f8c6dc7b048846763 kostenfrei http://asmp.eurasipjournals.com/content/2007/043218 kostenfrei https://doaj.org/toc/1687-4714 Journal toc kostenfrei https://doaj.org/toc/1687-4722 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ AR 2007 1, p 043218 |
| allfields_unstemmed |
(DE-627)DOAJ066318912 (DE-599)DOAJ0081f53b410f4e7f8c6dc7b048846763 DE-627 ger DE-627 rakwb eng QC221-246 QA75.5-76.95 Othman H verfasserin aut A Semi-Continuous State-Transition Probability HMM-Based Voice Activity Detector 2007 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier <p/< <p<We introduce an efficient hidden Markov model-based voice activity detection (VAD) algorithm with time-variant state-transition probabilities in the underlying Markov chain. The transition probabilities vary in an exponential charge/discharge scheme and are softly merged with state conditional likelihood into a final VAD decision. Working in the domain of ITU-T G.729 parameters, with no additional cost for feature extraction, the proposed algorithm significantly outperforms G.729 Annex B VAD while providing a balanced tradeoff between clipping and false detection errors. The performance compares very favorably with the adaptive multirate VAD, option 2 (AMR2).</p< Acoustics. Sound Electronic computers. Computer science Aboulnasr T verfasserin aut In EURASIP Journal on Audio, Speech, and Music Processing (2007), 1, p 043218 year:2007 number:1, p 043218 https://doaj.org/article/0081f53b410f4e7f8c6dc7b048846763 kostenfrei http://asmp.eurasipjournals.com/content/2007/043218 kostenfrei https://doaj.org/toc/1687-4714 Journal toc kostenfrei https://doaj.org/toc/1687-4722 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ AR 2007 1, p 043218 |
| allfieldsGer |
(DE-627)DOAJ066318912 (DE-599)DOAJ0081f53b410f4e7f8c6dc7b048846763 DE-627 ger DE-627 rakwb eng QC221-246 QA75.5-76.95 Othman H verfasserin aut A Semi-Continuous State-Transition Probability HMM-Based Voice Activity Detector 2007 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier <p/< <p<We introduce an efficient hidden Markov model-based voice activity detection (VAD) algorithm with time-variant state-transition probabilities in the underlying Markov chain. The transition probabilities vary in an exponential charge/discharge scheme and are softly merged with state conditional likelihood into a final VAD decision. Working in the domain of ITU-T G.729 parameters, with no additional cost for feature extraction, the proposed algorithm significantly outperforms G.729 Annex B VAD while providing a balanced tradeoff between clipping and false detection errors. The performance compares very favorably with the adaptive multirate VAD, option 2 (AMR2).</p< Acoustics. Sound Electronic computers. Computer science Aboulnasr T verfasserin aut In EURASIP Journal on Audio, Speech, and Music Processing (2007), 1, p 043218 year:2007 number:1, p 043218 https://doaj.org/article/0081f53b410f4e7f8c6dc7b048846763 kostenfrei http://asmp.eurasipjournals.com/content/2007/043218 kostenfrei https://doaj.org/toc/1687-4714 Journal toc kostenfrei https://doaj.org/toc/1687-4722 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ AR 2007 1, p 043218 |
| allfieldsSound |
(DE-627)DOAJ066318912 (DE-599)DOAJ0081f53b410f4e7f8c6dc7b048846763 DE-627 ger DE-627 rakwb eng QC221-246 QA75.5-76.95 Othman H verfasserin aut A Semi-Continuous State-Transition Probability HMM-Based Voice Activity Detector 2007 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier <p/< <p<We introduce an efficient hidden Markov model-based voice activity detection (VAD) algorithm with time-variant state-transition probabilities in the underlying Markov chain. The transition probabilities vary in an exponential charge/discharge scheme and are softly merged with state conditional likelihood into a final VAD decision. Working in the domain of ITU-T G.729 parameters, with no additional cost for feature extraction, the proposed algorithm significantly outperforms G.729 Annex B VAD while providing a balanced tradeoff between clipping and false detection errors. The performance compares very favorably with the adaptive multirate VAD, option 2 (AMR2).</p< Acoustics. Sound Electronic computers. Computer science Aboulnasr T verfasserin aut In EURASIP Journal on Audio, Speech, and Music Processing (2007), 1, p 043218 year:2007 number:1, p 043218 https://doaj.org/article/0081f53b410f4e7f8c6dc7b048846763 kostenfrei http://asmp.eurasipjournals.com/content/2007/043218 kostenfrei https://doaj.org/toc/1687-4714 Journal toc kostenfrei https://doaj.org/toc/1687-4722 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ AR 2007 1, p 043218 |
| language |
English |
| source |
In EURASIP Journal on Audio, Speech, and Music Processing (2007), 1, p 043218 year:2007 number:1, p 043218 |
| sourceStr |
In EURASIP Journal on Audio, Speech, and Music Processing (2007), 1, p 043218 year:2007 number:1, p 043218 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Acoustics. Sound Electronic computers. Computer science |
| isfreeaccess_bool |
true |
| container_title |
EURASIP Journal on Audio, Speech, and Music Processing |
| authorswithroles_txt_mv |
Othman H @@aut@@ Aboulnasr T @@aut@@ |
| publishDateDaySort_date |
2007-01-01T00:00:00Z |
| id |
DOAJ066318912 |
| 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">DOAJ066318912</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230309055916.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230228s2007 xx |||||o 00| ||eng c</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ066318912</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ0081f53b410f4e7f8c6dc7b048846763</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">QC221-246</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">QA75.5-76.95</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Othman H</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="2"><subfield code="a">A Semi-Continuous State-Transition Probability HMM-Based Voice Activity Detector</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2007</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"><p/< <p<We introduce an efficient hidden Markov model-based voice activity detection (VAD) algorithm with time-variant state-transition probabilities in the underlying Markov chain. The transition probabilities vary in an exponential charge/discharge scheme and are softly merged with state conditional likelihood into a final VAD decision. Working in the domain of ITU-T G.729 parameters, with no additional cost for feature extraction, the proposed algorithm significantly outperforms G.729 Annex B VAD while providing a balanced tradeoff between clipping and false detection errors. The performance compares very favorably with the adaptive multirate VAD, option 2 (AMR2).</p<</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Acoustics. Sound</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Electronic computers. Computer science</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Aboulnasr T</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">EURASIP Journal on Audio, Speech, and Music Processing</subfield><subfield code="g">(2007), 1, p 043218</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">year:2007</subfield><subfield code="g">number:1, p 043218</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/0081f53b410f4e7f8c6dc7b048846763</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">http://asmp.eurasipjournals.com/content/2007/043218</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/1687-4714</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/1687-4722</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="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="j">2007</subfield><subfield code="e">1, p 043218</subfield></datafield></record></collection>
|
| callnumber-first |
Q - Science |
| author |
Othman H |
| spellingShingle |
Othman H misc QC221-246 misc QA75.5-76.95 misc Acoustics. Sound misc Electronic computers. Computer science A Semi-Continuous State-Transition Probability HMM-Based Voice Activity Detector |
| authorStr |
Othman H |
| format |
electronic Article |
| delete_txt_mv |
keep |
| author_role |
aut aut |
| collection |
DOAJ |
| remote_str |
true |
| callnumber-label |
QC221-246 |
| illustrated |
Not Illustrated |
| topic_title |
QC221-246 QA75.5-76.95 A Semi-Continuous State-Transition Probability HMM-Based Voice Activity Detector |
| topic |
misc QC221-246 misc QA75.5-76.95 misc Acoustics. Sound misc Electronic computers. Computer science |
| topic_unstemmed |
misc QC221-246 misc QA75.5-76.95 misc Acoustics. Sound misc Electronic computers. Computer science |
| topic_browse |
misc QC221-246 misc QA75.5-76.95 misc Acoustics. Sound misc Electronic computers. Computer science |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
cr |
| hierarchy_parent_title |
EURASIP Journal on Audio, Speech, and Music Processing |
| hierarchy_top_title |
EURASIP Journal on Audio, Speech, and Music Processing |
| isfreeaccess_txt |
true |
| title |
A Semi-Continuous State-Transition Probability HMM-Based Voice Activity Detector |
| ctrlnum |
(DE-627)DOAJ066318912 (DE-599)DOAJ0081f53b410f4e7f8c6dc7b048846763 |
| title_full |
A Semi-Continuous State-Transition Probability HMM-Based Voice Activity Detector |
| author_sort |
Othman H |
| journal |
EURASIP Journal on Audio, Speech, and Music Processing |
| journalStr |
EURASIP Journal on Audio, Speech, and Music Processing |
| callnumber-first-code |
Q |
| lang_code |
eng |
| isOA_bool |
true |
| recordtype |
marc |
| publishDateSort |
2007 |
| contenttype_str_mv |
txt |
| author_browse |
Othman H Aboulnasr T |
| class |
QC221-246 QA75.5-76.95 |
| format_se |
Elektronische Aufsätze |
| author-letter |
Othman H |
| author2-role |
verfasserin |
| title_sort |
semi-continuous state-transition probability hmm-based voice activity detector |
| callnumber |
QC221-246 |
| title_auth |
A Semi-Continuous State-Transition Probability HMM-Based Voice Activity Detector |
| abstract |
<p/< <p<We introduce an efficient hidden Markov model-based voice activity detection (VAD) algorithm with time-variant state-transition probabilities in the underlying Markov chain. The transition probabilities vary in an exponential charge/discharge scheme and are softly merged with state conditional likelihood into a final VAD decision. Working in the domain of ITU-T G.729 parameters, with no additional cost for feature extraction, the proposed algorithm significantly outperforms G.729 Annex B VAD while providing a balanced tradeoff between clipping and false detection errors. The performance compares very favorably with the adaptive multirate VAD, option 2 (AMR2).</p< |
| abstractGer |
<p/< <p<We introduce an efficient hidden Markov model-based voice activity detection (VAD) algorithm with time-variant state-transition probabilities in the underlying Markov chain. The transition probabilities vary in an exponential charge/discharge scheme and are softly merged with state conditional likelihood into a final VAD decision. Working in the domain of ITU-T G.729 parameters, with no additional cost for feature extraction, the proposed algorithm significantly outperforms G.729 Annex B VAD while providing a balanced tradeoff between clipping and false detection errors. The performance compares very favorably with the adaptive multirate VAD, option 2 (AMR2).</p< |
| abstract_unstemmed |
<p/< <p<We introduce an efficient hidden Markov model-based voice activity detection (VAD) algorithm with time-variant state-transition probabilities in the underlying Markov chain. The transition probabilities vary in an exponential charge/discharge scheme and are softly merged with state conditional likelihood into a final VAD decision. Working in the domain of ITU-T G.729 parameters, with no additional cost for feature extraction, the proposed algorithm significantly outperforms G.729 Annex B VAD while providing a balanced tradeoff between clipping and false detection errors. The performance compares very favorably with the adaptive multirate VAD, option 2 (AMR2).</p< |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ |
| container_issue |
1, p 043218 |
| title_short |
A Semi-Continuous State-Transition Probability HMM-Based Voice Activity Detector |
| url |
https://doaj.org/article/0081f53b410f4e7f8c6dc7b048846763 http://asmp.eurasipjournals.com/content/2007/043218 https://doaj.org/toc/1687-4714 https://doaj.org/toc/1687-4722 |
| remote_bool |
true |
| author2 |
Aboulnasr T |
| author2Str |
Aboulnasr T |
| callnumber-subject |
QC - Physics |
| mediatype_str_mv |
c |
| isOA_txt |
true |
| hochschulschrift_bool |
false |
| callnumber-a |
QC221-246 |
| up_date |
2024-07-03T19:25:08.070Z |
| _version_ |
1803587114051305473 |
| 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">DOAJ066318912</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230309055916.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230228s2007 xx |||||o 00| ||eng c</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ066318912</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ0081f53b410f4e7f8c6dc7b048846763</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">QC221-246</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">QA75.5-76.95</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Othman H</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="2"><subfield code="a">A Semi-Continuous State-Transition Probability HMM-Based Voice Activity Detector</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2007</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"><p/< <p<We introduce an efficient hidden Markov model-based voice activity detection (VAD) algorithm with time-variant state-transition probabilities in the underlying Markov chain. The transition probabilities vary in an exponential charge/discharge scheme and are softly merged with state conditional likelihood into a final VAD decision. Working in the domain of ITU-T G.729 parameters, with no additional cost for feature extraction, the proposed algorithm significantly outperforms G.729 Annex B VAD while providing a balanced tradeoff between clipping and false detection errors. The performance compares very favorably with the adaptive multirate VAD, option 2 (AMR2).</p<</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Acoustics. Sound</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Electronic computers. Computer science</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Aboulnasr T</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">EURASIP Journal on Audio, Speech, and Music Processing</subfield><subfield code="g">(2007), 1, p 043218</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">year:2007</subfield><subfield code="g">number:1, p 043218</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/0081f53b410f4e7f8c6dc7b048846763</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">http://asmp.eurasipjournals.com/content/2007/043218</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/1687-4714</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/1687-4722</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="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="j">2007</subfield><subfield code="e">1, p 043218</subfield></datafield></record></collection>
|
| score |
7.401598 |