Noisy speech recognition using temporal AM-FM combination
The efficiency of multistream speech recognizers is investigated by performing several experiments. In order to take advantage of multistream features, each stream should compensate the weakness of the other streams. Our objective is to utilize frequency modulation (FM) which can compensate errors f...
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 | 4712 |
|---|---|
| container_issue | |
| container_start_page | 4709 |
| container_title | |
| container_volume | |
| creator | Kubo, Y. Kurematsu, A. Shirai, K. Okawa, S. |
| description | The efficiency of multistream speech recognizers is investigated by performing several experiments. In order to take advantage of multistream features, each stream should compensate the weakness of the other streams. Our objective is to utilize frequency modulation (FM) which can compensate errors from traditional analysis methods. In order to achieve informational independence from other features based on the spectral/time envelope of signals, our features do not contain amplitude information, but contain temporal structure information of frequency modulation. Our method is evaluated by the continuous digit recognition of noisy speech. We confirmed that our AM-FM combination method is efficient for noisy speech recognition. |
| doi_str_mv | 10.1109/ICASSP.2008.4518708 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_4518708</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4518708</ieee_id><sourcerecordid>4518708</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-bec8c085c6063cdafc5b6970a2bcba5f9da8c0154efd96cf6c4a06602e69972d3</originalsourceid><addsrcrecordid>eNo1kMtOwzAURM1LIpR8QTf5AYfrt--yqiggtYBUkNhVjuMUo-ahJCz69wRRZjOLMxqNhpA5g5wxwLun5WK7fc05gM2lYtaAPSM3THIpmbQSz0nChUHKED4uSIrG_jMhLknCFAeqmcRrkg7DF0ySSihUCcHnNg7HbOhC8J9ZH3y7b-IY2yb7HmKzz8ZQd23vDtliQ1ebzLd1ERv3G7glV5U7DCE9-Yy8r-7flo90_fIw7V3TyIwaaRG89WCV16CFL13lVaHRgOOFL5yqsHQTZ0qGqkTtK-2lA62BB41oeClmZP7XG0MIu66PteuPu9ML4geT_00D</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Noisy speech recognition using temporal AM-FM combination</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Kubo, Y. ; Kurematsu, A. ; Shirai, K. ; Okawa, S.</creator><creatorcontrib>Kubo, Y. ; Kurematsu, A. ; Shirai, K. ; Okawa, S.</creatorcontrib><description>The efficiency of multistream speech recognizers is investigated by performing several experiments. In order to take advantage of multistream features, each stream should compensate the weakness of the other streams. Our objective is to utilize frequency modulation (FM) which can compensate errors from traditional analysis methods. In order to achieve informational independence from other features based on the spectral/time envelope of signals, our features do not contain amplitude information, but contain temporal structure information of frequency modulation. Our method is evaluated by the continuous digit recognition of noisy speech. We confirmed that our AM-FM combination method is efficient for noisy speech recognition.</description><identifier>ISSN: 1520-6149</identifier><identifier>ISBN: 9781424414833</identifier><identifier>ISBN: 1424414830</identifier><identifier>EISSN: 2379-190X</identifier><identifier>EISBN: 1424414849</identifier><identifier>EISBN: 9781424414840</identifier><identifier>DOI: 10.1109/ICASSP.2008.4518708</identifier><language>eng</language><publisher>IEEE</publisher><subject>Amplitude modulation ; Computer errors ; Computer science ; Error analysis ; Feature extraction ; Filter bank ; Frequency modulation ; Humans ; multistream features ; Speech analysis ; Speech recognition ; temporal analysis</subject><ispartof>2008 IEEE International Conference on Acoustics, Speech and Signal Processing, 2008, p.4709-4712</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/4518708$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,777,781,786,787,2052,27906,54901</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4518708$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Kubo, Y.</creatorcontrib><creatorcontrib>Kurematsu, A.</creatorcontrib><creatorcontrib>Shirai, K.</creatorcontrib><creatorcontrib>Okawa, S.</creatorcontrib><title>Noisy speech recognition using temporal AM-FM combination</title><title>2008 IEEE International Conference on Acoustics, Speech and Signal Processing</title><addtitle>ICASSP</addtitle><description>The efficiency of multistream speech recognizers is investigated by performing several experiments. In order to take advantage of multistream features, each stream should compensate the weakness of the other streams. Our objective is to utilize frequency modulation (FM) which can compensate errors from traditional analysis methods. In order to achieve informational independence from other features based on the spectral/time envelope of signals, our features do not contain amplitude information, but contain temporal structure information of frequency modulation. Our method is evaluated by the continuous digit recognition of noisy speech. We confirmed that our AM-FM combination method is efficient for noisy speech recognition.</description><subject>Amplitude modulation</subject><subject>Computer errors</subject><subject>Computer science</subject><subject>Error analysis</subject><subject>Feature extraction</subject><subject>Filter bank</subject><subject>Frequency modulation</subject><subject>Humans</subject><subject>multistream features</subject><subject>Speech analysis</subject><subject>Speech recognition</subject><subject>temporal analysis</subject><issn>1520-6149</issn><issn>2379-190X</issn><isbn>9781424414833</isbn><isbn>1424414830</isbn><isbn>1424414849</isbn><isbn>9781424414840</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2008</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNo1kMtOwzAURM1LIpR8QTf5AYfrt--yqiggtYBUkNhVjuMUo-ahJCz69wRRZjOLMxqNhpA5g5wxwLun5WK7fc05gM2lYtaAPSM3THIpmbQSz0nChUHKED4uSIrG_jMhLknCFAeqmcRrkg7DF0ySSihUCcHnNg7HbOhC8J9ZH3y7b-IY2yb7HmKzz8ZQd23vDtliQ1ebzLd1ERv3G7glV5U7DCE9-Yy8r-7flo90_fIw7V3TyIwaaRG89WCV16CFL13lVaHRgOOFL5yqsHQTZ0qGqkTtK-2lA62BB41oeClmZP7XG0MIu66PteuPu9ML4geT_00D</recordid><startdate>200803</startdate><enddate>200803</enddate><creator>Kubo, Y.</creator><creator>Kurematsu, A.</creator><creator>Shirai, K.</creator><creator>Okawa, S.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>200803</creationdate><title>Noisy speech recognition using temporal AM-FM combination</title><author>Kubo, Y. ; Kurematsu, A. ; Shirai, K. ; Okawa, S.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-bec8c085c6063cdafc5b6970a2bcba5f9da8c0154efd96cf6c4a06602e69972d3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2008</creationdate><topic>Amplitude modulation</topic><topic>Computer errors</topic><topic>Computer science</topic><topic>Error analysis</topic><topic>Feature extraction</topic><topic>Filter bank</topic><topic>Frequency modulation</topic><topic>Humans</topic><topic>multistream features</topic><topic>Speech analysis</topic><topic>Speech recognition</topic><topic>temporal analysis</topic><toplevel>online_resources</toplevel><creatorcontrib>Kubo, Y.</creatorcontrib><creatorcontrib>Kurematsu, A.</creatorcontrib><creatorcontrib>Shirai, K.</creatorcontrib><creatorcontrib>Okawa, S.</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 Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Kubo, Y.</au><au>Kurematsu, A.</au><au>Shirai, K.</au><au>Okawa, S.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Noisy speech recognition using temporal AM-FM combination</atitle><btitle>2008 IEEE International Conference on Acoustics, Speech and Signal Processing</btitle><stitle>ICASSP</stitle><date>2008-03</date><risdate>2008</risdate><spage>4709</spage><epage>4712</epage><pages>4709-4712</pages><issn>1520-6149</issn><eissn>2379-190X</eissn><isbn>9781424414833</isbn><isbn>1424414830</isbn><eisbn>1424414849</eisbn><eisbn>9781424414840</eisbn><abstract>The efficiency of multistream speech recognizers is investigated by performing several experiments. In order to take advantage of multistream features, each stream should compensate the weakness of the other streams. Our objective is to utilize frequency modulation (FM) which can compensate errors from traditional analysis methods. In order to achieve informational independence from other features based on the spectral/time envelope of signals, our features do not contain amplitude information, but contain temporal structure information of frequency modulation. Our method is evaluated by the continuous digit recognition of noisy speech. We confirmed that our AM-FM combination method is efficient for noisy speech recognition.</abstract><pub>IEEE</pub><doi>10.1109/ICASSP.2008.4518708</doi><tpages>4</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1520-6149 |
| ispartof | 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, 2008, p.4709-4712 |
| issn | 1520-6149 2379-190X |
| language | eng |
| recordid | cdi_ieee_primary_4518708 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Amplitude modulation Computer errors Computer science Error analysis Feature extraction Filter bank Frequency modulation Humans multistream features Speech analysis Speech recognition temporal analysis |
| title | Noisy speech recognition using temporal AM-FM combination |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-20T23%3A35%3A30IST&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=Noisy%20speech%20recognition%20using%20temporal%20AM-FM%20combination&rft.btitle=2008%20IEEE%20International%20Conference%20on%20Acoustics,%20Speech%20and%20Signal%20Processing&rft.au=Kubo,%20Y.&rft.date=2008-03&rft.spage=4709&rft.epage=4712&rft.pages=4709-4712&rft.issn=1520-6149&rft.eissn=2379-190X&rft.isbn=9781424414833&rft.isbn_list=1424414830&rft_id=info:doi/10.1109/ICASSP.2008.4518708&rft_dat=%3Cieee_6IE%3E4518708%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=1424414849&rft.eisbn_list=9781424414840&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=4518708&rfr_iscdi=true |