Voice-activity home care system
This work proposes a voice-activity home care system which can construct a life log associated with voices at home. Accordingly, the techniques of sound-pressure-level calculation, abnormal sound detection, noise reduction, text-independent speaker recognition and keyword spotting are developed. In...
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 | 113 |
|---|---|
| container_issue | |
| container_start_page | 110 |
| container_title | |
| container_volume | |
| creator | Chen, Oscal T.-C Tsai, Y. H. Su, C. W. Kuo, P. C. Lai, W. C. |
| description | This work proposes a voice-activity home care system which can construct a life log associated with voices at home. Accordingly, the techniques of sound-pressure-level calculation, abnormal sound detection, noise reduction, text-independent speaker recognition and keyword spotting are developed. In abnormal sound detection and speaker recognition, we adopt the two-stage recognition processes of Gaussian Mixture Model (GMM) for sound rejection, and Support Vector Machine (SVM) for sound classification. The experimental results reveal that the proposed abnormal sound detection, speaker recognition, and word spotting can reach accuracy rates above 82%, 90%, and 87%, respectively. Based on the recognized abnormal sounds or special words, an emergent event can be identified for home care where a speaker is known as well. Finally, the abovementioned recognition results versus time scales can fairly build a daily life log for home care. |
| doi_str_mv | 10.1109/BHI.2016.7455847 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_7455847</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>7455847</ieee_id><sourcerecordid>1808627823</sourcerecordid><originalsourceid>FETCH-LOGICAL-i156t-84ffd575b07ea84763dacf217654fc745e5f15d1c1587dc7f4088d416a0ed4833</originalsourceid><addsrcrecordid>eNqNkE9Lw0AQxVdBsNbeBQ_m6CVxZrP_ctRSbaHgRb2GdTOLK4mp2VTIt3el_QDOZXjDe48fw9gVQoEI1d3DelNwQFVoIaUR-oRdoIQKeJL6lM04KpNzDuacLWL8hDQmnSo1YzdvfXCUWzeGnzBO2UffUebsQFmc4kjdJTvzto20OO45e31cvSzX-fb5abO83-YBpRpzI7xvpJbvoMkmAlU21nmOWknhXcIi6VE26FAa3TjtBRjTCFQWqBGmLOfs9tC7G_rvPcWx7kJ01Lb2i_p9rDEBAy9T7B9WMIprw_9arw_WQET1bgidHab6-KXyF323WDQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype><pqid>1808627823</pqid></control><display><type>conference_proceeding</type><title>Voice-activity home care system</title><source>IEEE Electronic Library (IEL)</source><creator>Chen, Oscal T.-C ; Tsai, Y. H. ; Su, C. W. ; Kuo, P. C. ; Lai, W. C.</creator><creatorcontrib>Chen, Oscal T.-C ; Tsai, Y. H. ; Su, C. W. ; Kuo, P. C. ; Lai, W. C.</creatorcontrib><description>This work proposes a voice-activity home care system which can construct a life log associated with voices at home. Accordingly, the techniques of sound-pressure-level calculation, abnormal sound detection, noise reduction, text-independent speaker recognition and keyword spotting are developed. In abnormal sound detection and speaker recognition, we adopt the two-stage recognition processes of Gaussian Mixture Model (GMM) for sound rejection, and Support Vector Machine (SVM) for sound classification. The experimental results reveal that the proposed abnormal sound detection, speaker recognition, and word spotting can reach accuracy rates above 82%, 90%, and 87%, respectively. Based on the recognized abnormal sounds or special words, an emergent event can be identified for home care where a speaker is known as well. Finally, the abovementioned recognition results versus time scales can fairly build a daily life log for home care.</description><identifier>EISSN: 2168-2208</identifier><identifier>EISBN: 1509024557</identifier><identifier>EISBN: 9781509024551</identifier><identifier>DOI: 10.1109/BHI.2016.7455847</identifier><language>eng</language><publisher>IEEE</publisher><subject>CARE system ; Conferences ; Construction ; Context ; daily log ; Gaussian mixture model ; Health ; keyword spotting ; Noise reduction ; Recognition ; Signal to noise ratio ; Sound ; Speaker recognition ; Special sound recognition ; Speech ; Speech recognition ; support vector machine ; Support vector machines</subject><ispartof>2016 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI), 2016, p.110-113</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/7455847$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,314,780,784,789,790,796,23929,23930,25139,27923,27924,54757</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/7455847$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Chen, Oscal T.-C</creatorcontrib><creatorcontrib>Tsai, Y. H.</creatorcontrib><creatorcontrib>Su, C. W.</creatorcontrib><creatorcontrib>Kuo, P. C.</creatorcontrib><creatorcontrib>Lai, W. C.</creatorcontrib><title>Voice-activity home care system</title><title>2016 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)</title><addtitle>BHI</addtitle><description>This work proposes a voice-activity home care system which can construct a life log associated with voices at home. Accordingly, the techniques of sound-pressure-level calculation, abnormal sound detection, noise reduction, text-independent speaker recognition and keyword spotting are developed. In abnormal sound detection and speaker recognition, we adopt the two-stage recognition processes of Gaussian Mixture Model (GMM) for sound rejection, and Support Vector Machine (SVM) for sound classification. The experimental results reveal that the proposed abnormal sound detection, speaker recognition, and word spotting can reach accuracy rates above 82%, 90%, and 87%, respectively. Based on the recognized abnormal sounds or special words, an emergent event can be identified for home care where a speaker is known as well. Finally, the abovementioned recognition results versus time scales can fairly build a daily life log for home care.</description><subject>CARE system</subject><subject>Conferences</subject><subject>Construction</subject><subject>Context</subject><subject>daily log</subject><subject>Gaussian mixture model</subject><subject>Health</subject><subject>keyword spotting</subject><subject>Noise reduction</subject><subject>Recognition</subject><subject>Signal to noise ratio</subject><subject>Sound</subject><subject>Speaker recognition</subject><subject>Special sound recognition</subject><subject>Speech</subject><subject>Speech recognition</subject><subject>support vector machine</subject><subject>Support vector machines</subject><issn>2168-2208</issn><isbn>1509024557</isbn><isbn>9781509024551</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2016</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNqNkE9Lw0AQxVdBsNbeBQ_m6CVxZrP_ctRSbaHgRb2GdTOLK4mp2VTIt3el_QDOZXjDe48fw9gVQoEI1d3DelNwQFVoIaUR-oRdoIQKeJL6lM04KpNzDuacLWL8hDQmnSo1YzdvfXCUWzeGnzBO2UffUebsQFmc4kjdJTvzto20OO45e31cvSzX-fb5abO83-YBpRpzI7xvpJbvoMkmAlU21nmOWknhXcIi6VE26FAa3TjtBRjTCFQWqBGmLOfs9tC7G_rvPcWx7kJ01Lb2i_p9rDEBAy9T7B9WMIprw_9arw_WQET1bgidHab6-KXyF323WDQ</recordid><startdate>20160201</startdate><enddate>20160201</enddate><creator>Chen, Oscal T.-C</creator><creator>Tsai, Y. H.</creator><creator>Su, C. W.</creator><creator>Kuo, P. C.</creator><creator>Lai, W. C.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope><scope>7QO</scope><scope>8FD</scope><scope>FR3</scope><scope>P64</scope><scope>7SC</scope><scope>7SP</scope><scope>7U5</scope><scope>F28</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>20160201</creationdate><title>Voice-activity home care system</title><author>Chen, Oscal T.-C ; Tsai, Y. H. ; Su, C. W. ; Kuo, P. C. ; Lai, W. C.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i156t-84ffd575b07ea84763dacf217654fc745e5f15d1c1587dc7f4088d416a0ed4833</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2016</creationdate><topic>CARE system</topic><topic>Conferences</topic><topic>Construction</topic><topic>Context</topic><topic>daily log</topic><topic>Gaussian mixture model</topic><topic>Health</topic><topic>keyword spotting</topic><topic>Noise reduction</topic><topic>Recognition</topic><topic>Signal to noise ratio</topic><topic>Sound</topic><topic>Speaker recognition</topic><topic>Special sound recognition</topic><topic>Speech</topic><topic>Speech recognition</topic><topic>support vector machine</topic><topic>Support vector machines</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Chen, Oscal T.-C</creatorcontrib><creatorcontrib>Tsai, Y. H.</creatorcontrib><creatorcontrib>Su, C. W.</creatorcontrib><creatorcontrib>Kuo, P. C.</creatorcontrib><creatorcontrib>Lai, W. C.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection><collection>Biotechnology Research Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Chen, Oscal T.-C</au><au>Tsai, Y. H.</au><au>Su, C. W.</au><au>Kuo, P. C.</au><au>Lai, W. C.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Voice-activity home care system</atitle><btitle>2016 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)</btitle><stitle>BHI</stitle><date>2016-02-01</date><risdate>2016</risdate><spage>110</spage><epage>113</epage><pages>110-113</pages><eissn>2168-2208</eissn><eisbn>1509024557</eisbn><eisbn>9781509024551</eisbn><abstract>This work proposes a voice-activity home care system which can construct a life log associated with voices at home. Accordingly, the techniques of sound-pressure-level calculation, abnormal sound detection, noise reduction, text-independent speaker recognition and keyword spotting are developed. In abnormal sound detection and speaker recognition, we adopt the two-stage recognition processes of Gaussian Mixture Model (GMM) for sound rejection, and Support Vector Machine (SVM) for sound classification. The experimental results reveal that the proposed abnormal sound detection, speaker recognition, and word spotting can reach accuracy rates above 82%, 90%, and 87%, respectively. Based on the recognized abnormal sounds or special words, an emergent event can be identified for home care where a speaker is known as well. Finally, the abovementioned recognition results versus time scales can fairly build a daily life log for home care.</abstract><pub>IEEE</pub><doi>10.1109/BHI.2016.7455847</doi><tpages>4</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | EISSN: 2168-2208 |
| ispartof | 2016 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI), 2016, p.110-113 |
| issn | 2168-2208 |
| language | eng |
| recordid | cdi_ieee_primary_7455847 |
| source | IEEE Electronic Library (IEL) |
| subjects | CARE system Conferences Construction Context daily log Gaussian mixture model Health keyword spotting Noise reduction Recognition Signal to noise ratio Sound Speaker recognition Special sound recognition Speech Speech recognition support vector machine Support vector machines |
| title | Voice-activity home care system |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-12T07%3A59%3A49IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Voice-activity%20home%20care%20system&rft.btitle=2016%20IEEE-EMBS%20International%20Conference%20on%20Biomedical%20and%20Health%20Informatics%20(BHI)&rft.au=Chen,%20Oscal%20T.-C&rft.date=2016-02-01&rft.spage=110&rft.epage=113&rft.pages=110-113&rft.eissn=2168-2208&rft_id=info:doi/10.1109/BHI.2016.7455847&rft_dat=%3Cproquest_RIE%3E1808627823%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&rft.eisbn=1509024557&rft.eisbn_list=9781509024551&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1808627823&rft_id=info:pmid/&rft_ieee_id=7455847&rfr_iscdi=true |