Cepstral analysis based on the glimpse proportion measure for improving the intelligibility of HMM-based synthetic speech in noise
In this paper we introduce a new cepstral coefficient extraction method based on an intelligibility measure for speech in noise, the Glimpse Proportion measure. This new method aims to increase the intelligibility of speech in noise by modifying the clean speech, and has applications in scenarios su...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 4000 |
|---|---|
| container_issue | |
| container_start_page | 3997 |
| container_title | |
| container_volume | |
| creator | Valentini-Botinhao, C. Maia, R. Yamagishi, J. King, S. Zen, H. |
| description | In this paper we introduce a new cepstral coefficient extraction method based on an intelligibility measure for speech in noise, the Glimpse Proportion measure. This new method aims to increase the intelligibility of speech in noise by modifying the clean speech, and has applications in scenarios such as public announcement and car navigation systems. We first explain how the Glimpse Proportion measure operates and further show how we approximated it to integrate it into an existing spectral envelope parameter extraction method commonly used in the HMM-based speech synthesis framework. We then demonstrate how this new method changes the modelled spectrum according to the characteristics of the noise and show results for a listening test with vocoded and HMM-based synthetic speech. The test indicates that the proposed method can significantly improve intelligibility of synthetic speech in speech shaped noise. |
| doi_str_mv | 10.1109/ICASSP.2012.6288794 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6288794</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6288794</ieee_id><sourcerecordid>6288794</sourcerecordid><originalsourceid>FETCH-LOGICAL-i220t-1e07fcd989ceb65dfc0c4eda0b721d1812cff12115d9bc8b4fbab57ca1aa92cc3</originalsourceid><addsrcrecordid>eNo1kN1KAzEQheMfWGufoDd5gV0z2exPLqWoFVoUquBdSbKTNpLuLskq7K1P7mLr3AzM-c6BM4TMgaUATN49L-43m9eUM-BpwauqlOKMzGRZgSjKjDFRyHMy4VkpE5Ds44Lc_Au5uCQTyDlLChDymsxi_GTjjFaWFRPys8Au9kF5qhrlh-gi1SpiTduG9nukO-8OXUTahbZrQ-_G8wFV_ApIbRvoKIb22zW7P9g1PXrvdk477_qBtpYu1-vkGBiHZmR6Z2jsEM1-pGnTuoi35MoqH3F22lPy_vjwtlgmq5ensfgqcZyzPgFkpTW1rKRBXeS1NcwIrBXTJYcaKuDGWuAAeS21qbSwWum8NAqUktyYbErmx1yHiNsuuIMKw_b0zuwXzVFplA</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Cepstral analysis based on the glimpse proportion measure for improving the intelligibility of HMM-based synthetic speech in noise</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Valentini-Botinhao, C. ; Maia, R. ; Yamagishi, J. ; King, S. ; Zen, H.</creator><creatorcontrib>Valentini-Botinhao, C. ; Maia, R. ; Yamagishi, J. ; King, S. ; Zen, H.</creatorcontrib><description>In this paper we introduce a new cepstral coefficient extraction method based on an intelligibility measure for speech in noise, the Glimpse Proportion measure. This new method aims to increase the intelligibility of speech in noise by modifying the clean speech, and has applications in scenarios such as public announcement and car navigation systems. We first explain how the Glimpse Proportion measure operates and further show how we approximated it to integrate it into an existing spectral envelope parameter extraction method commonly used in the HMM-based speech synthesis framework. We then demonstrate how this new method changes the modelled spectrum according to the characteristics of the noise and show results for a listening test with vocoded and HMM-based synthetic speech. The test indicates that the proposed method can significantly improve intelligibility of synthetic speech in speech shaped noise.</description><identifier>ISSN: 1520-6149</identifier><identifier>ISBN: 1467300454</identifier><identifier>ISBN: 9781467300452</identifier><identifier>EISSN: 2379-190X</identifier><identifier>EISBN: 9781467300469</identifier><identifier>EISBN: 1467300446</identifier><identifier>EISBN: 9781467300445</identifier><identifier>EISBN: 1467300462</identifier><identifier>DOI: 10.1109/ICASSP.2012.6288794</identifier><language>eng</language><publisher>IEEE</publisher><subject>Accuracy ; Approximation methods ; Cepstral analysis ; cepstral coefficient extraction ; Hidden Markov models ; HMM-based speech synthesis ; Lombard speech ; Noise ; Noise measurement ; objective measure for speech intelligibility ; Speech</subject><ispartof>2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2012, p.3997-4000</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6288794$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,27902,54895</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6288794$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Valentini-Botinhao, C.</creatorcontrib><creatorcontrib>Maia, R.</creatorcontrib><creatorcontrib>Yamagishi, J.</creatorcontrib><creatorcontrib>King, S.</creatorcontrib><creatorcontrib>Zen, H.</creatorcontrib><title>Cepstral analysis based on the glimpse proportion measure for improving the intelligibility of HMM-based synthetic speech in noise</title><title>2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</title><addtitle>ICASSP</addtitle><description>In this paper we introduce a new cepstral coefficient extraction method based on an intelligibility measure for speech in noise, the Glimpse Proportion measure. This new method aims to increase the intelligibility of speech in noise by modifying the clean speech, and has applications in scenarios such as public announcement and car navigation systems. We first explain how the Glimpse Proportion measure operates and further show how we approximated it to integrate it into an existing spectral envelope parameter extraction method commonly used in the HMM-based speech synthesis framework. We then demonstrate how this new method changes the modelled spectrum according to the characteristics of the noise and show results for a listening test with vocoded and HMM-based synthetic speech. The test indicates that the proposed method can significantly improve intelligibility of synthetic speech in speech shaped noise.</description><subject>Accuracy</subject><subject>Approximation methods</subject><subject>Cepstral analysis</subject><subject>cepstral coefficient extraction</subject><subject>Hidden Markov models</subject><subject>HMM-based speech synthesis</subject><subject>Lombard speech</subject><subject>Noise</subject><subject>Noise measurement</subject><subject>objective measure for speech intelligibility</subject><subject>Speech</subject><issn>1520-6149</issn><issn>2379-190X</issn><isbn>1467300454</isbn><isbn>9781467300452</isbn><isbn>9781467300469</isbn><isbn>1467300446</isbn><isbn>9781467300445</isbn><isbn>1467300462</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2012</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNo1kN1KAzEQheMfWGufoDd5gV0z2exPLqWoFVoUquBdSbKTNpLuLskq7K1P7mLr3AzM-c6BM4TMgaUATN49L-43m9eUM-BpwauqlOKMzGRZgSjKjDFRyHMy4VkpE5Ds44Lc_Au5uCQTyDlLChDymsxi_GTjjFaWFRPys8Au9kF5qhrlh-gi1SpiTduG9nukO-8OXUTahbZrQ-_G8wFV_ApIbRvoKIb22zW7P9g1PXrvdk477_qBtpYu1-vkGBiHZmR6Z2jsEM1-pGnTuoi35MoqH3F22lPy_vjwtlgmq5ensfgqcZyzPgFkpTW1rKRBXeS1NcwIrBXTJYcaKuDGWuAAeS21qbSwWum8NAqUktyYbErmx1yHiNsuuIMKw_b0zuwXzVFplA</recordid><startdate>20120101</startdate><enddate>20120101</enddate><creator>Valentini-Botinhao, C.</creator><creator>Maia, R.</creator><creator>Yamagishi, J.</creator><creator>King, S.</creator><creator>Zen, H.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>20120101</creationdate><title>Cepstral analysis based on the glimpse proportion measure for improving the intelligibility of HMM-based synthetic speech in noise</title><author>Valentini-Botinhao, C. ; Maia, R. ; Yamagishi, J. ; King, S. ; Zen, H.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i220t-1e07fcd989ceb65dfc0c4eda0b721d1812cff12115d9bc8b4fbab57ca1aa92cc3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2012</creationdate><topic>Accuracy</topic><topic>Approximation methods</topic><topic>Cepstral analysis</topic><topic>cepstral coefficient extraction</topic><topic>Hidden Markov models</topic><topic>HMM-based speech synthesis</topic><topic>Lombard speech</topic><topic>Noise</topic><topic>Noise measurement</topic><topic>objective measure for speech intelligibility</topic><topic>Speech</topic><toplevel>online_resources</toplevel><creatorcontrib>Valentini-Botinhao, C.</creatorcontrib><creatorcontrib>Maia, R.</creatorcontrib><creatorcontrib>Yamagishi, J.</creatorcontrib><creatorcontrib>King, S.</creatorcontrib><creatorcontrib>Zen, H.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Xplore</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Valentini-Botinhao, C.</au><au>Maia, R.</au><au>Yamagishi, J.</au><au>King, S.</au><au>Zen, H.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Cepstral analysis based on the glimpse proportion measure for improving the intelligibility of HMM-based synthetic speech in noise</atitle><btitle>2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</btitle><stitle>ICASSP</stitle><date>2012-01-01</date><risdate>2012</risdate><spage>3997</spage><epage>4000</epage><pages>3997-4000</pages><issn>1520-6149</issn><eissn>2379-190X</eissn><isbn>1467300454</isbn><isbn>9781467300452</isbn><eisbn>9781467300469</eisbn><eisbn>1467300446</eisbn><eisbn>9781467300445</eisbn><eisbn>1467300462</eisbn><abstract>In this paper we introduce a new cepstral coefficient extraction method based on an intelligibility measure for speech in noise, the Glimpse Proportion measure. This new method aims to increase the intelligibility of speech in noise by modifying the clean speech, and has applications in scenarios such as public announcement and car navigation systems. We first explain how the Glimpse Proportion measure operates and further show how we approximated it to integrate it into an existing spectral envelope parameter extraction method commonly used in the HMM-based speech synthesis framework. We then demonstrate how this new method changes the modelled spectrum according to the characteristics of the noise and show results for a listening test with vocoded and HMM-based synthetic speech. The test indicates that the proposed method can significantly improve intelligibility of synthetic speech in speech shaped noise.</abstract><pub>IEEE</pub><doi>10.1109/ICASSP.2012.6288794</doi><tpages>4</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1520-6149 |
| ispartof | 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2012, p.3997-4000 |
| issn | 1520-6149 2379-190X |
| language | eng |
| recordid | cdi_ieee_primary_6288794 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Accuracy Approximation methods Cepstral analysis cepstral coefficient extraction Hidden Markov models HMM-based speech synthesis Lombard speech Noise Noise measurement objective measure for speech intelligibility Speech |
| title | Cepstral analysis based on the glimpse proportion measure for improving the intelligibility of HMM-based synthetic speech in noise |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-11T20%3A46%3A01IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Cepstral%20analysis%20based%20on%20the%20glimpse%20proportion%20measure%20for%20improving%20the%20intelligibility%20of%20HMM-based%20synthetic%20speech%20in%20noise&rft.btitle=2012%20IEEE%20International%20Conference%20on%20Acoustics,%20Speech%20and%20Signal%20Processing%20(ICASSP)&rft.au=Valentini-Botinhao,%20C.&rft.date=2012-01-01&rft.spage=3997&rft.epage=4000&rft.pages=3997-4000&rft.issn=1520-6149&rft.eissn=2379-190X&rft.isbn=1467300454&rft.isbn_list=9781467300452&rft_id=info:doi/10.1109/ICASSP.2012.6288794&rft_dat=%3Cieee_6IE%3E6288794%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781467300469&rft.eisbn_list=1467300446&rft.eisbn_list=9781467300445&rft.eisbn_list=1467300462&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6288794&rfr_iscdi=true |