Method for training speech recognition model, device and storage medium
A method for training a speech recognition model, a device and a storage medium, which relate to the field of computer technologies, and particularly to the fields of speech recognition technologies, deep learning technologies, or the like, are disclosed. The method for training a speech recognition...
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 | Chen, Zhijie Shao, Junyao Qian, Sheng Zang, Qiguang Liang, Mingxin Zheng, Huanxin Fu, Xiaoyin |
| description | A method for training a speech recognition model, a device and a storage medium, which relate to the field of computer technologies, and particularly to the fields of speech recognition technologies, deep learning technologies, or the like, are disclosed. The method for training a speech recognition model includes: obtaining a fusion probability of each of at least one candidate text corresponding to a speech based on an acoustic decoding model and a language model; selecting a preset number of one or more candidate texts based on the fusion probability of each of the at least one candidate text, and determining a predicted text based on the preset number of one or more candidate texts; and obtaining a loss function based on the predicted text and a standard text corresponding to the speech, and training the speech recognition model based on the loss function. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US12033616B2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US12033616B2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US12033616B23</originalsourceid><addsrcrecordid>eNqNyjsOwjAQBUA3FAi4w9KDRGIpBwDxaaiAOrLsl2SleNeyDeen4QBU08zSXO-okwYaNFPNjoVlpJIAP1GG11G4sgpFDZh3FPBhD3ISqFTNbgRFBH7HtVkMbi7Y_FyZ7eX8PN32SNqjJOchqP3r0bQHa7umO7b2n_MFWmwz4Q</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Method for training speech recognition model, device and storage medium</title><source>esp@cenet</source><creator>Chen, Zhijie ; Shao, Junyao ; Qian, Sheng ; Zang, Qiguang ; Liang, Mingxin ; Zheng, Huanxin ; Fu, Xiaoyin</creator><creatorcontrib>Chen, Zhijie ; Shao, Junyao ; Qian, Sheng ; Zang, Qiguang ; Liang, Mingxin ; Zheng, Huanxin ; Fu, Xiaoyin</creatorcontrib><description>A method for training a speech recognition model, a device and a storage medium, which relate to the field of computer technologies, and particularly to the fields of speech recognition technologies, deep learning technologies, or the like, are disclosed. The method for training a speech recognition model includes: obtaining a fusion probability of each of at least one candidate text corresponding to a speech based on an acoustic decoding model and a language model; selecting a preset number of one or more candidate texts based on the fusion probability of each of the at least one candidate text, and determining a predicted text based on the preset number of one or more candidate texts; and obtaining a loss function based on the predicted text and a standard text corresponding to the speech, and training the speech recognition model based on the loss function.</description><language>eng</language><subject>ACOUSTICS ; MUSICAL INSTRUMENTS ; PHYSICS ; SPEECH ANALYSIS OR SYNTHESIS ; SPEECH OR AUDIO CODING OR DECODING ; SPEECH OR VOICE PROCESSING ; SPEECH RECOGNITION</subject><creationdate>2024</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=20240709&DB=EPODOC&CC=US&NR=12033616B2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240709&DB=EPODOC&CC=US&NR=12033616B2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Chen, Zhijie</creatorcontrib><creatorcontrib>Shao, Junyao</creatorcontrib><creatorcontrib>Qian, Sheng</creatorcontrib><creatorcontrib>Zang, Qiguang</creatorcontrib><creatorcontrib>Liang, Mingxin</creatorcontrib><creatorcontrib>Zheng, Huanxin</creatorcontrib><creatorcontrib>Fu, Xiaoyin</creatorcontrib><title>Method for training speech recognition model, device and storage medium</title><description>A method for training a speech recognition model, a device and a storage medium, which relate to the field of computer technologies, and particularly to the fields of speech recognition technologies, deep learning technologies, or the like, are disclosed. The method for training a speech recognition model includes: obtaining a fusion probability of each of at least one candidate text corresponding to a speech based on an acoustic decoding model and a language model; selecting a preset number of one or more candidate texts based on the fusion probability of each of the at least one candidate text, and determining a predicted text based on the preset number of one or more candidate texts; and obtaining a loss function based on the predicted text and a standard text corresponding to the speech, and training the speech recognition model based on the loss function.</description><subject>ACOUSTICS</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>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNyjsOwjAQBUA3FAi4w9KDRGIpBwDxaaiAOrLsl2SleNeyDeen4QBU08zSXO-okwYaNFPNjoVlpJIAP1GG11G4sgpFDZh3FPBhD3ISqFTNbgRFBH7HtVkMbi7Y_FyZ7eX8PN32SNqjJOchqP3r0bQHa7umO7b2n_MFWmwz4Q</recordid><startdate>20240709</startdate><enddate>20240709</enddate><creator>Chen, Zhijie</creator><creator>Shao, Junyao</creator><creator>Qian, Sheng</creator><creator>Zang, Qiguang</creator><creator>Liang, Mingxin</creator><creator>Zheng, Huanxin</creator><creator>Fu, Xiaoyin</creator><scope>EVB</scope></search><sort><creationdate>20240709</creationdate><title>Method for training speech recognition model, device and storage medium</title><author>Chen, Zhijie ; Shao, Junyao ; Qian, Sheng ; Zang, Qiguang ; Liang, Mingxin ; Zheng, Huanxin ; Fu, Xiaoyin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US12033616B23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2024</creationdate><topic>ACOUSTICS</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>Chen, Zhijie</creatorcontrib><creatorcontrib>Shao, Junyao</creatorcontrib><creatorcontrib>Qian, Sheng</creatorcontrib><creatorcontrib>Zang, Qiguang</creatorcontrib><creatorcontrib>Liang, Mingxin</creatorcontrib><creatorcontrib>Zheng, Huanxin</creatorcontrib><creatorcontrib>Fu, Xiaoyin</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Chen, Zhijie</au><au>Shao, Junyao</au><au>Qian, Sheng</au><au>Zang, Qiguang</au><au>Liang, Mingxin</au><au>Zheng, Huanxin</au><au>Fu, Xiaoyin</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Method for training speech recognition model, device and storage medium</title><date>2024-07-09</date><risdate>2024</risdate><abstract>A method for training a speech recognition model, a device and a storage medium, which relate to the field of computer technologies, and particularly to the fields of speech recognition technologies, deep learning technologies, or the like, are disclosed. The method for training a speech recognition model includes: obtaining a fusion probability of each of at least one candidate text corresponding to a speech based on an acoustic decoding model and a language model; selecting a preset number of one or more candidate texts based on the fusion probability of each of the at least one candidate text, and determining a predicted text based on the preset number of one or more candidate texts; and obtaining a loss function based on the predicted text and a standard text corresponding to the speech, and training the speech recognition model based on the loss function.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US12033616B2 |
| source | esp@cenet |
| subjects | ACOUSTICS MUSICAL INSTRUMENTS PHYSICS SPEECH ANALYSIS OR SYNTHESIS SPEECH OR AUDIO CODING OR DECODING SPEECH OR VOICE PROCESSING SPEECH RECOGNITION |
| title | Method for training speech recognition model, device and storage medium |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-20T05%3A29%3A37IST&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=Chen,%20Zhijie&rft.date=2024-07-09&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS12033616B2%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 |