Voice recognition network, method and equipment based on cross-layer connection attention and medium
The invention is suitable for the technical field of speech recognition, and provides a speech recognition network, method and device based on cross-layer connection attention and a storage medium, the speech recognition network is constructed based on a Transform encoder-decoder structure, a Transf...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; 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 | ZHANG TIANHAO YIN XUCHENG CHEN SONGLU |
| description | The invention is suitable for the technical field of speech recognition, and provides a speech recognition network, method and device based on cross-layer connection attention and a storage medium, the speech recognition network is constructed based on a Transform encoder-decoder structure, a Transform encoder of the speech recognition network comprises a plurality of encoding layers, a cross-layer connection module is connected between the adjacent encoding layers, and the cross-layer connection module is connected between the adjacent encoding layers. The coding layer is used for learning information of a middle attention map of a previous coding layer through a cross-layer connection module when the attention map is generated, so that the attention map generated by each coding layer can more accurately express a dependency relationship of a context; therefore, the speech recognition accuracy of the speech recognition network is remarkably improved under the condition that almost neglectable parameter quant |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN114360507A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN114360507A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN114360507A3</originalsourceid><addsrcrecordid>eNqNjb0KwjAURrs4iPoO191CS_2ZpShOTuJaYvJVg829NUkR395QfACn7wzn8E0zcxWrQR5a7myjFSZGfIt_rsghPsSQYkN4DbZ34Eg3FWAoadpLCHmnPvCkhRl6rFWMSRspdQ7GDm6eTVrVBSx-O8uWx8OlPuXopUHolUY6bepzWa6rbbEpdvvqH-cLDyM_JA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Voice recognition network, method and equipment based on cross-layer connection attention and medium</title><source>esp@cenet</source><creator>ZHANG TIANHAO ; YIN XUCHENG ; CHEN SONGLU</creator><creatorcontrib>ZHANG TIANHAO ; YIN XUCHENG ; CHEN SONGLU</creatorcontrib><description>The invention is suitable for the technical field of speech recognition, and provides a speech recognition network, method and device based on cross-layer connection attention and a storage medium, the speech recognition network is constructed based on a Transform encoder-decoder structure, a Transform encoder of the speech recognition network comprises a plurality of encoding layers, a cross-layer connection module is connected between the adjacent encoding layers, and the cross-layer connection module is connected between the adjacent encoding layers. The coding layer is used for learning information of a middle attention map of a previous coding layer through a cross-layer connection module when the attention map is generated, so that the attention map generated by each coding layer can more accurately express a dependency relationship of a context; therefore, the speech recognition accuracy of the speech recognition network is remarkably improved under the condition that almost neglectable parameter quant</description><language>chi ; eng</language><subject>ACOUSTICS ; CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; MUSICAL INSTRUMENTS ; PHYSICS ; SPEECH ANALYSIS OR SYNTHESIS ; SPEECH OR AUDIO CODING OR DECODING ; SPEECH OR VOICE PROCESSING ; SPEECH RECOGNITION</subject><creationdate>2022</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=20220415&DB=EPODOC&CC=CN&NR=114360507A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25544,76293</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220415&DB=EPODOC&CC=CN&NR=114360507A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZHANG TIANHAO</creatorcontrib><creatorcontrib>YIN XUCHENG</creatorcontrib><creatorcontrib>CHEN SONGLU</creatorcontrib><title>Voice recognition network, method and equipment based on cross-layer connection attention and medium</title><description>The invention is suitable for the technical field of speech recognition, and provides a speech recognition network, method and device based on cross-layer connection attention and a storage medium, the speech recognition network is constructed based on a Transform encoder-decoder structure, a Transform encoder of the speech recognition network comprises a plurality of encoding layers, a cross-layer connection module is connected between the adjacent encoding layers, and the cross-layer connection module is connected between the adjacent encoding layers. The coding layer is used for learning information of a middle attention map of a previous coding layer through a cross-layer connection module when the attention map is generated, so that the attention map generated by each coding layer can more accurately express a dependency relationship of a context; therefore, the speech recognition accuracy of the speech recognition network is remarkably improved under the condition that almost neglectable parameter quant</description><subject>ACOUSTICS</subject><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</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>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNjb0KwjAURrs4iPoO191CS_2ZpShOTuJaYvJVg829NUkR395QfACn7wzn8E0zcxWrQR5a7myjFSZGfIt_rsghPsSQYkN4DbZ34Eg3FWAoadpLCHmnPvCkhRl6rFWMSRspdQ7GDm6eTVrVBSx-O8uWx8OlPuXopUHolUY6bepzWa6rbbEpdvvqH-cLDyM_JA</recordid><startdate>20220415</startdate><enddate>20220415</enddate><creator>ZHANG TIANHAO</creator><creator>YIN XUCHENG</creator><creator>CHEN SONGLU</creator><scope>EVB</scope></search><sort><creationdate>20220415</creationdate><title>Voice recognition network, method and equipment based on cross-layer connection attention and medium</title><author>ZHANG TIANHAO ; YIN XUCHENG ; CHEN SONGLU</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN114360507A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</creationdate><topic>ACOUSTICS</topic><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</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>ZHANG TIANHAO</creatorcontrib><creatorcontrib>YIN XUCHENG</creatorcontrib><creatorcontrib>CHEN SONGLU</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZHANG TIANHAO</au><au>YIN XUCHENG</au><au>CHEN SONGLU</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Voice recognition network, method and equipment based on cross-layer connection attention and medium</title><date>2022-04-15</date><risdate>2022</risdate><abstract>The invention is suitable for the technical field of speech recognition, and provides a speech recognition network, method and device based on cross-layer connection attention and a storage medium, the speech recognition network is constructed based on a Transform encoder-decoder structure, a Transform encoder of the speech recognition network comprises a plurality of encoding layers, a cross-layer connection module is connected between the adjacent encoding layers, and the cross-layer connection module is connected between the adjacent encoding layers. The coding layer is used for learning information of a middle attention map of a previous coding layer through a cross-layer connection module when the attention map is generated, so that the attention map generated by each coding layer can more accurately express a dependency relationship of a context; therefore, the speech recognition accuracy of the speech recognition network is remarkably improved under the condition that almost neglectable parameter quant</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN114360507A |
| source | esp@cenet |
| subjects | ACOUSTICS CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING MUSICAL INSTRUMENTS PHYSICS SPEECH ANALYSIS OR SYNTHESIS SPEECH OR AUDIO CODING OR DECODING SPEECH OR VOICE PROCESSING SPEECH RECOGNITION |
| title | Voice recognition network, method and equipment based on cross-layer connection attention and medium |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-27T14%3A39%3A11IST&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=ZHANG%20TIANHAO&rft.date=2022-04-15&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN114360507A%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 |