Voice activity detection based on using wavelet packet
This paper, presents a robust voice activity detection (VAD) technique based on wavelet packet. In this technique sub-bands and their amplitudes are represented as the vectors for each sample time in order to find a new feature from the frequency and amplitude changes. On the other hand, the multi-r...
Gespeichert in:
| Veröffentlicht in: | Digital signal processing 2010-07, Vol.20 (4), p.1102-1115 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1115 |
|---|---|
| container_issue | 4 |
| container_start_page | 1102 |
| container_title | Digital signal processing |
| container_volume | 20 |
| creator | Eshaghi, Mohadese Karami Mollaei, M.R. |
| description | This paper, presents a robust voice activity detection (VAD) technique based on wavelet packet. In this technique sub-bands and their amplitudes are represented as the vectors for each sample time in order to find a new feature from the frequency and amplitude changes. On the other hand, the multi-resolution analysis property of the wavelet packet transform (WPT), the voiced, unvoiced, and transient components of speech can be distinctly discriminated. Then, a new feature extraction method is implemented based on observations of the angles between vectors. This feature extraction method retains most unvoiced sounds in a voice active frame. Experimental results show that the proposed WT feature parameter can extract the speech activity under poor SNR conditions and that it is also insensitive to variable-level of noise. |
| doi_str_mv | 10.1016/j.dsp.2009.11.008 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_914629245</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S1051200409002449</els_id><sourcerecordid>914629245</sourcerecordid><originalsourceid>FETCH-LOGICAL-c329t-95eba54f66d644eec161f59e2939a4eba7003edaad4e5b0ebc7f8ee1df7af6ab3</originalsourceid><addsrcrecordid>eNp9kLtOwzAUhi0EEqXwAGzZmBJ8YsepxYQqblIlFmC1HPsYuaRJsN2ivj2uysx0fum_SOcj5BpoBRTE7bqycapqSmUFUFG6OCEzoLIpOWPs9KAbKLPNz8lFjGtKactrMSPiY_QGC22S3_m0LywmzHocik5HtEUW2-iHz-JH77DHVEzafGG6JGdO9xGv_u6cvD8-vC2fy9Xr08vyflUaVstUygY73XAnhBWcIxoQ4BqJtWRS8-y1lDK0WluOTUexM61bIIJ1rXZCd2xObo67Uxi_txiT2vhosO_1gOM2Kglc1LLmTU7CMWnCGGNAp6bgNzrsFVB1QKTWKiNSB0QKQGVEuXN37GB-YecxqGg8DgatD5mCsqP_p_0L00dv0A</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>914629245</pqid></control><display><type>article</type><title>Voice activity detection based on using wavelet packet</title><source>Elsevier ScienceDirect Journals Complete</source><creator>Eshaghi, Mohadese ; Karami Mollaei, M.R.</creator><creatorcontrib>Eshaghi, Mohadese ; Karami Mollaei, M.R.</creatorcontrib><description>This paper, presents a robust voice activity detection (VAD) technique based on wavelet packet. In this technique sub-bands and their amplitudes are represented as the vectors for each sample time in order to find a new feature from the frequency and amplitude changes. On the other hand, the multi-resolution analysis property of the wavelet packet transform (WPT), the voiced, unvoiced, and transient components of speech can be distinctly discriminated. Then, a new feature extraction method is implemented based on observations of the angles between vectors. This feature extraction method retains most unvoiced sounds in a voice active frame. Experimental results show that the proposed WT feature parameter can extract the speech activity under poor SNR conditions and that it is also insensitive to variable-level of noise.</description><identifier>ISSN: 1051-2004</identifier><identifier>EISSN: 1095-4333</identifier><identifier>DOI: 10.1016/j.dsp.2009.11.008</identifier><language>eng</language><publisher>Elsevier Inc</publisher><subject>Amplitudes ; Discrete wavelet packet ; Feature extraction ; Mathematical analysis ; Speech ; Speech processing ; Transforms ; Vectors (mathematics) ; Voice ; Voice activity detection ; Wavelet</subject><ispartof>Digital signal processing, 2010-07, Vol.20 (4), p.1102-1115</ispartof><rights>2009 Elsevier Inc.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c329t-95eba54f66d644eec161f59e2939a4eba7003edaad4e5b0ebc7f8ee1df7af6ab3</citedby><cites>FETCH-LOGICAL-c329t-95eba54f66d644eec161f59e2939a4eba7003edaad4e5b0ebc7f8ee1df7af6ab3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.dsp.2009.11.008$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,780,784,3550,27924,27925,45995</link.rule.ids></links><search><creatorcontrib>Eshaghi, Mohadese</creatorcontrib><creatorcontrib>Karami Mollaei, M.R.</creatorcontrib><title>Voice activity detection based on using wavelet packet</title><title>Digital signal processing</title><description>This paper, presents a robust voice activity detection (VAD) technique based on wavelet packet. In this technique sub-bands and their amplitudes are represented as the vectors for each sample time in order to find a new feature from the frequency and amplitude changes. On the other hand, the multi-resolution analysis property of the wavelet packet transform (WPT), the voiced, unvoiced, and transient components of speech can be distinctly discriminated. Then, a new feature extraction method is implemented based on observations of the angles between vectors. This feature extraction method retains most unvoiced sounds in a voice active frame. Experimental results show that the proposed WT feature parameter can extract the speech activity under poor SNR conditions and that it is also insensitive to variable-level of noise.</description><subject>Amplitudes</subject><subject>Discrete wavelet packet</subject><subject>Feature extraction</subject><subject>Mathematical analysis</subject><subject>Speech</subject><subject>Speech processing</subject><subject>Transforms</subject><subject>Vectors (mathematics)</subject><subject>Voice</subject><subject>Voice activity detection</subject><subject>Wavelet</subject><issn>1051-2004</issn><issn>1095-4333</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2010</creationdate><recordtype>article</recordtype><recordid>eNp9kLtOwzAUhi0EEqXwAGzZmBJ8YsepxYQqblIlFmC1HPsYuaRJsN2ivj2uysx0fum_SOcj5BpoBRTE7bqycapqSmUFUFG6OCEzoLIpOWPs9KAbKLPNz8lFjGtKactrMSPiY_QGC22S3_m0LywmzHocik5HtEUW2-iHz-JH77DHVEzafGG6JGdO9xGv_u6cvD8-vC2fy9Xr08vyflUaVstUygY73XAnhBWcIxoQ4BqJtWRS8-y1lDK0WluOTUexM61bIIJ1rXZCd2xObo67Uxi_txiT2vhosO_1gOM2Kglc1LLmTU7CMWnCGGNAp6bgNzrsFVB1QKTWKiNSB0QKQGVEuXN37GB-YecxqGg8DgatD5mCsqP_p_0L00dv0A</recordid><startdate>20100701</startdate><enddate>20100701</enddate><creator>Eshaghi, Mohadese</creator><creator>Karami Mollaei, M.R.</creator><general>Elsevier Inc</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>20100701</creationdate><title>Voice activity detection based on using wavelet packet</title><author>Eshaghi, Mohadese ; Karami Mollaei, M.R.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c329t-95eba54f66d644eec161f59e2939a4eba7003edaad4e5b0ebc7f8ee1df7af6ab3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2010</creationdate><topic>Amplitudes</topic><topic>Discrete wavelet packet</topic><topic>Feature extraction</topic><topic>Mathematical analysis</topic><topic>Speech</topic><topic>Speech processing</topic><topic>Transforms</topic><topic>Vectors (mathematics)</topic><topic>Voice</topic><topic>Voice activity detection</topic><topic>Wavelet</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Eshaghi, Mohadese</creatorcontrib><creatorcontrib>Karami Mollaei, M.R.</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</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><jtitle>Digital signal processing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Eshaghi, Mohadese</au><au>Karami Mollaei, M.R.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Voice activity detection based on using wavelet packet</atitle><jtitle>Digital signal processing</jtitle><date>2010-07-01</date><risdate>2010</risdate><volume>20</volume><issue>4</issue><spage>1102</spage><epage>1115</epage><pages>1102-1115</pages><issn>1051-2004</issn><eissn>1095-4333</eissn><abstract>This paper, presents a robust voice activity detection (VAD) technique based on wavelet packet. In this technique sub-bands and their amplitudes are represented as the vectors for each sample time in order to find a new feature from the frequency and amplitude changes. On the other hand, the multi-resolution analysis property of the wavelet packet transform (WPT), the voiced, unvoiced, and transient components of speech can be distinctly discriminated. Then, a new feature extraction method is implemented based on observations of the angles between vectors. This feature extraction method retains most unvoiced sounds in a voice active frame. Experimental results show that the proposed WT feature parameter can extract the speech activity under poor SNR conditions and that it is also insensitive to variable-level of noise.</abstract><pub>Elsevier Inc</pub><doi>10.1016/j.dsp.2009.11.008</doi><tpages>14</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1051-2004 |
| ispartof | Digital signal processing, 2010-07, Vol.20 (4), p.1102-1115 |
| issn | 1051-2004 1095-4333 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_914629245 |
| source | Elsevier ScienceDirect Journals Complete |
| subjects | Amplitudes Discrete wavelet packet Feature extraction Mathematical analysis Speech Speech processing Transforms Vectors (mathematics) Voice Voice activity detection Wavelet |
| title | Voice activity detection based on using wavelet packet |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T11%3A36%3A44IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Voice%20activity%20detection%20based%20on%20using%20wavelet%20packet&rft.jtitle=Digital%20signal%20processing&rft.au=Eshaghi,%20Mohadese&rft.date=2010-07-01&rft.volume=20&rft.issue=4&rft.spage=1102&rft.epage=1115&rft.pages=1102-1115&rft.issn=1051-2004&rft.eissn=1095-4333&rft_id=info:doi/10.1016/j.dsp.2009.11.008&rft_dat=%3Cproquest_cross%3E914629245%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=914629245&rft_id=info:pmid/&rft_els_id=S1051200409002449&rfr_iscdi=true |