Diarization Driven by Meta-Information Identified in Discussion Content
An approach is provided that receives an audio stream and utilizes a voice activation detection (VAD) process to create a digital audio stream of voices from at least two different speakers. An automatic speech recognition (ASR) process is applied to the digital stream with the ASR process resulting...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Patent |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Fousek, Petr Novak, Miroslav Saon, George A Church, Kenneth W Dimitriadis, Dimitrios B |
| description | An approach is provided that receives an audio stream and utilizes a voice activation detection (VAD) process to create a digital audio stream of voices from at least two different speakers. An automatic speech recognition (ASR) process is applied to the digital stream with the ASR process resulting in the spoken words to which a speaker turn detection (STD) process is applied to identify a number of speaker segments with each speaker segment ending at a word boundary. The STD process analyzes a number of speaker segments using a language model that determines when speaker changes occur. A speaker clustering algorithm is then applied to the speaker segments to associate one of the speakers with each of the speaker segments. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2019156835A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2019156835A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2019156835A13</originalsourceid><addsrcrecordid>eNrjZHB3yUwsyqxKLMnMz1NwKcosS81TSKpU8E0tSdT1zEvLL8qFSHmmpOaVZKZlpqYoZAIVZhYnlxYXgySc8_NKgFI8DKxpiTnFqbxQmptB2c01xNlDN7UgPz61uCAxOTUvtSQ-NNjIwNDS0NTMwtjU0dCYOFUAK0c02A</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Diarization Driven by Meta-Information Identified in Discussion Content</title><source>esp@cenet</source><creator>Fousek, Petr ; Novak, Miroslav ; Saon, George A ; Church, Kenneth W ; Dimitriadis, Dimitrios B</creator><creatorcontrib>Fousek, Petr ; Novak, Miroslav ; Saon, George A ; Church, Kenneth W ; Dimitriadis, Dimitrios B</creatorcontrib><description>An approach is provided that receives an audio stream and utilizes a voice activation detection (VAD) process to create a digital audio stream of voices from at least two different speakers. An automatic speech recognition (ASR) process is applied to the digital stream with the ASR process resulting in the spoken words to which a speaker turn detection (STD) process is applied to identify a number of speaker segments with each speaker segment ending at a word boundary. The STD process analyzes a number of speaker segments using a language model that determines when speaker changes occur. A speaker clustering algorithm is then applied to the speaker segments to associate one of the speakers with each of the speaker segments.</description><language>eng</language><subject>ACOUSTICS ; CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; MUSICAL INSTRUMENTS ; PHYSICS ; SPEECH ANALYSIS OR SYNTHESIS ; SPEECH OR AUDIO CODING OR DECODING ; SPEECH OR VOICE PROCESSING ; SPEECH RECOGNITION</subject><creationdate>2019</creationdate><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://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20190523&DB=EPODOC&CC=US&NR=2019156835A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25544,76293</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20190523&DB=EPODOC&CC=US&NR=2019156835A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Fousek, Petr</creatorcontrib><creatorcontrib>Novak, Miroslav</creatorcontrib><creatorcontrib>Saon, George A</creatorcontrib><creatorcontrib>Church, Kenneth W</creatorcontrib><creatorcontrib>Dimitriadis, Dimitrios B</creatorcontrib><title>Diarization Driven by Meta-Information Identified in Discussion Content</title><description>An approach is provided that receives an audio stream and utilizes a voice activation detection (VAD) process to create a digital audio stream of voices from at least two different speakers. An automatic speech recognition (ASR) process is applied to the digital stream with the ASR process resulting in the spoken words to which a speaker turn detection (STD) process is applied to identify a number of speaker segments with each speaker segment ending at a word boundary. The STD process analyzes a number of speaker segments using a language model that determines when speaker changes occur. A speaker clustering algorithm is then applied to the speaker segments to associate one of the speakers with each of the speaker segments.</description><subject>ACOUSTICS</subject><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>MUSICAL INSTRUMENTS</subject><subject>PHYSICS</subject><subject>SPEECH ANALYSIS OR SYNTHESIS</subject><subject>SPEECH OR AUDIO CODING OR DECODING</subject><subject>SPEECH OR VOICE PROCESSING</subject><subject>SPEECH RECOGNITION</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2019</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZHB3yUwsyqxKLMnMz1NwKcosS81TSKpU8E0tSdT1zEvLL8qFSHmmpOaVZKZlpqYoZAIVZhYnlxYXgySc8_NKgFI8DKxpiTnFqbxQmptB2c01xNlDN7UgPz61uCAxOTUvtSQ-NNjIwNDS0NTMwtjU0dCYOFUAK0c02A</recordid><startdate>20190523</startdate><enddate>20190523</enddate><creator>Fousek, Petr</creator><creator>Novak, Miroslav</creator><creator>Saon, George A</creator><creator>Church, Kenneth W</creator><creator>Dimitriadis, Dimitrios B</creator><scope>EVB</scope></search><sort><creationdate>20190523</creationdate><title>Diarization Driven by Meta-Information Identified in Discussion Content</title><author>Fousek, Petr ; Novak, Miroslav ; Saon, George A ; Church, Kenneth W ; Dimitriadis, Dimitrios B</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2019156835A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2019</creationdate><topic>ACOUSTICS</topic><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>MUSICAL INSTRUMENTS</topic><topic>PHYSICS</topic><topic>SPEECH ANALYSIS OR SYNTHESIS</topic><topic>SPEECH OR AUDIO CODING OR DECODING</topic><topic>SPEECH OR VOICE PROCESSING</topic><topic>SPEECH RECOGNITION</topic><toplevel>online_resources</toplevel><creatorcontrib>Fousek, Petr</creatorcontrib><creatorcontrib>Novak, Miroslav</creatorcontrib><creatorcontrib>Saon, George A</creatorcontrib><creatorcontrib>Church, Kenneth W</creatorcontrib><creatorcontrib>Dimitriadis, Dimitrios B</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Fousek, Petr</au><au>Novak, Miroslav</au><au>Saon, George A</au><au>Church, Kenneth W</au><au>Dimitriadis, Dimitrios B</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Diarization Driven by Meta-Information Identified in Discussion Content</title><date>2019-05-23</date><risdate>2019</risdate><abstract>An approach is provided that receives an audio stream and utilizes a voice activation detection (VAD) process to create a digital audio stream of voices from at least two different speakers. An automatic speech recognition (ASR) process is applied to the digital stream with the ASR process resulting in the spoken words to which a speaker turn detection (STD) process is applied to identify a number of speaker segments with each speaker segment ending at a word boundary. The STD process analyzes a number of speaker segments using a language model that determines when speaker changes occur. A speaker clustering algorithm is then applied to the speaker segments to associate one of the speakers with each of the speaker segments.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US2019156835A1 |
| source | esp@cenet |
| subjects | ACOUSTICS CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING MUSICAL INSTRUMENTS PHYSICS SPEECH ANALYSIS OR SYNTHESIS SPEECH OR AUDIO CODING OR DECODING SPEECH OR VOICE PROCESSING SPEECH RECOGNITION |
| title | Diarization Driven by Meta-Information Identified in Discussion Content |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-27T17%3A26%3A10IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=Fousek,%20Petr&rft.date=2019-05-23&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2019156835A1%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |