Asynchronous optimization for sequence training of neural networks
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, by a first sequence-training speech model, a first batch of training frames that represent speech features of first training utterances; obtaining, by the first sequence-training speech...
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 | Senior, Andrew W Heigold, Georg Mcdermott, Erik Vanhoucke, Vincent O Bacchiani, Michiel A. U |
| description | Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, by a first sequence-training speech model, a first batch of training frames that represent speech features of first training utterances; obtaining, by the first sequence-training speech model, one or more first neural network parameters; determining, by the first sequence-training speech model, one or more optimized first neural network parameters based on (i) the first batch of training frames and (ii) the one or more first neural network parameters; obtaining, by a second sequence-training speech model, a second batch of training frames that represent speech features of second training utterances; obtaining one or more second neural network parameters; and determining, by the second sequence-training speech model, one or more optimized second neural network parameters based on (i) the second batch of training frames and (ii) the one or more second neural network parameters. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US11854534B1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US11854534B1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US11854534B13</originalsourceid><addsrcrecordid>eNrjZHByLK7MS84oys_LLy1WyC8oyczNrEosyczPU0jLL1IoTi0sTc1LTlUoKUrMzMvMS1fIT1PISy0tSswBUiXl-UXZxTwMrGmJOcWpvFCam0HRzTXE2UM3tSA_PrW4IDE5Fag0PjTY0NDC1MTU2MTJ0JgYNQDJ8zNB</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Asynchronous optimization for sequence training of neural networks</title><source>esp@cenet</source><creator>Senior, Andrew W ; Heigold, Georg ; Mcdermott, Erik ; Vanhoucke, Vincent O ; Bacchiani, Michiel A. U</creator><creatorcontrib>Senior, Andrew W ; Heigold, Georg ; Mcdermott, Erik ; Vanhoucke, Vincent O ; Bacchiani, Michiel A. U</creatorcontrib><description>Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, by a first sequence-training speech model, a first batch of training frames that represent speech features of first training utterances; obtaining, by the first sequence-training speech model, one or more first neural network parameters; determining, by the first sequence-training speech model, one or more optimized first neural network parameters based on (i) the first batch of training frames and (ii) the one or more first neural network parameters; obtaining, by a second sequence-training speech model, a second batch of training frames that represent speech features of second training utterances; obtaining one or more second neural network parameters; and determining, by the second sequence-training speech model, one or more optimized second neural network parameters based on (i) the second batch of training frames and (ii) the one or more second neural network parameters.</description><language>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>2023</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=20231226&DB=EPODOC&CC=US&NR=11854534B1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76516</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20231226&DB=EPODOC&CC=US&NR=11854534B1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Senior, Andrew W</creatorcontrib><creatorcontrib>Heigold, Georg</creatorcontrib><creatorcontrib>Mcdermott, Erik</creatorcontrib><creatorcontrib>Vanhoucke, Vincent O</creatorcontrib><creatorcontrib>Bacchiani, Michiel A. U</creatorcontrib><title>Asynchronous optimization for sequence training of neural networks</title><description>Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, by a first sequence-training speech model, a first batch of training frames that represent speech features of first training utterances; obtaining, by the first sequence-training speech model, one or more first neural network parameters; determining, by the first sequence-training speech model, one or more optimized first neural network parameters based on (i) the first batch of training frames and (ii) the one or more first neural network parameters; obtaining, by a second sequence-training speech model, a second batch of training frames that represent speech features of second training utterances; obtaining one or more second neural network parameters; and determining, by the second sequence-training speech model, one or more optimized second neural network parameters based on (i) the second batch of training frames and (ii) the one or more second neural network parameters.</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>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZHByLK7MS84oys_LLy1WyC8oyczNrEosyczPU0jLL1IoTi0sTc1LTlUoKUrMzMvMS1fIT1PISy0tSswBUiXl-UXZxTwMrGmJOcWpvFCam0HRzTXE2UM3tSA_PrW4IDE5Fag0PjTY0NDC1MTU2MTJ0JgYNQDJ8zNB</recordid><startdate>20231226</startdate><enddate>20231226</enddate><creator>Senior, Andrew W</creator><creator>Heigold, Georg</creator><creator>Mcdermott, Erik</creator><creator>Vanhoucke, Vincent O</creator><creator>Bacchiani, Michiel A. U</creator><scope>EVB</scope></search><sort><creationdate>20231226</creationdate><title>Asynchronous optimization for sequence training of neural networks</title><author>Senior, Andrew W ; Heigold, Georg ; Mcdermott, Erik ; Vanhoucke, Vincent O ; Bacchiani, Michiel A. U</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US11854534B13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2023</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>Senior, Andrew W</creatorcontrib><creatorcontrib>Heigold, Georg</creatorcontrib><creatorcontrib>Mcdermott, Erik</creatorcontrib><creatorcontrib>Vanhoucke, Vincent O</creatorcontrib><creatorcontrib>Bacchiani, Michiel A. U</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Senior, Andrew W</au><au>Heigold, Georg</au><au>Mcdermott, Erik</au><au>Vanhoucke, Vincent O</au><au>Bacchiani, Michiel A. U</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Asynchronous optimization for sequence training of neural networks</title><date>2023-12-26</date><risdate>2023</risdate><abstract>Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, by a first sequence-training speech model, a first batch of training frames that represent speech features of first training utterances; obtaining, by the first sequence-training speech model, one or more first neural network parameters; determining, by the first sequence-training speech model, one or more optimized first neural network parameters based on (i) the first batch of training frames and (ii) the one or more first neural network parameters; obtaining, by a second sequence-training speech model, a second batch of training frames that represent speech features of second training utterances; obtaining one or more second neural network parameters; and determining, by the second sequence-training speech model, one or more optimized second neural network parameters based on (i) the second batch of training frames and (ii) the one or more second neural network parameters.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US11854534B1 |
| 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 | Asynchronous optimization for sequence training of neural networks |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-13T14%3A13%3A58IST&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=Senior,%20Andrew%20W&rft.date=2023-12-26&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS11854534B1%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 |