CUSTOM DISPLAY POST PROCESSING IN SPEECH RECOGNITION
Solutions for custom display post processing (DPP) in speech recognition (SR) use a customized multi-stage DPP pipeline that transforms a stream of SR tokens from lexical form to display form. A first transformation stage of the DPP pipeline receives the stream of tokens, in turn, by an upstream fil...
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 | RAHMEL, Heiko Willy CHANG, Shuangyu ZHAO, Che BEHRE, Piyush KIBRE, Nicholas SHAHID, Khuram VARADHARAJAN, Padma LIN, Edward C LIU, Wei |
| description | Solutions for custom display post processing (DPP) in speech recognition (SR) use a customized multi-stage DPP pipeline that transforms a stream of SR tokens from lexical form to display form. A first transformation stage of the DPP pipeline receives the stream of tokens, in turn, by an upstream filter, a base model stage, and a downstream filter, and transforms a first aspect of the stream of tokens (e.g., disfluency, inverse text normalization (ITN), capitalization, etc.) from lexical form into display form. The upstream filter and/or the downstream filter alter the stream of tokens to change the default behavior of the DPP pipeline into custom behavior. Additional transformation stages of the DPP pipeline perform further transforms, allowing for outputting final text in a display format that is customized for a specific user. This permits each user to efficiently leverage a common baseline DPP pipeline to produce a custom output. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2024403539A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2024403539A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2024403539A13</originalsourceid><addsrcrecordid>eNrjZDBxDg0O8fdVcPEMDvBxjFQI8A8OUQgI8nd2DQ729HNX8PRTCA5wdXX2UAhydfZ39_MM8fT342FgTUvMKU7lhdLcDMpuriHOHrqpBfnxqcUFicmpeakl8aHBRgZGJiYGxqbGlo6GxsSpAgCFFCiT</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>CUSTOM DISPLAY POST PROCESSING IN SPEECH RECOGNITION</title><source>esp@cenet</source><creator>RAHMEL, Heiko Willy ; CHANG, Shuangyu ; ZHAO, Che ; BEHRE, Piyush ; KIBRE, Nicholas ; SHAHID, Khuram ; VARADHARAJAN, Padma ; LIN, Edward C ; LIU, Wei</creator><creatorcontrib>RAHMEL, Heiko Willy ; CHANG, Shuangyu ; ZHAO, Che ; BEHRE, Piyush ; KIBRE, Nicholas ; SHAHID, Khuram ; VARADHARAJAN, Padma ; LIN, Edward C ; LIU, Wei</creatorcontrib><description>Solutions for custom display post processing (DPP) in speech recognition (SR) use a customized multi-stage DPP pipeline that transforms a stream of SR tokens from lexical form to display form. A first transformation stage of the DPP pipeline receives the stream of tokens, in turn, by an upstream filter, a base model stage, and a downstream filter, and transforms a first aspect of the stream of tokens (e.g., disfluency, inverse text normalization (ITN), capitalization, etc.) from lexical form into display form. The upstream filter and/or the downstream filter alter the stream of tokens to change the default behavior of the DPP pipeline into custom behavior. Additional transformation stages of the DPP pipeline perform further transforms, allowing for outputting final text in a display format that is customized for a specific user. This permits each user to efficiently leverage a common baseline DPP pipeline to produce a custom output.</description><language>eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</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=20241205&DB=EPODOC&CC=US&NR=2024403539A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25543,76293</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20241205&DB=EPODOC&CC=US&NR=2024403539A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>RAHMEL, Heiko Willy</creatorcontrib><creatorcontrib>CHANG, Shuangyu</creatorcontrib><creatorcontrib>ZHAO, Che</creatorcontrib><creatorcontrib>BEHRE, Piyush</creatorcontrib><creatorcontrib>KIBRE, Nicholas</creatorcontrib><creatorcontrib>SHAHID, Khuram</creatorcontrib><creatorcontrib>VARADHARAJAN, Padma</creatorcontrib><creatorcontrib>LIN, Edward C</creatorcontrib><creatorcontrib>LIU, Wei</creatorcontrib><title>CUSTOM DISPLAY POST PROCESSING IN SPEECH RECOGNITION</title><description>Solutions for custom display post processing (DPP) in speech recognition (SR) use a customized multi-stage DPP pipeline that transforms a stream of SR tokens from lexical form to display form. A first transformation stage of the DPP pipeline receives the stream of tokens, in turn, by an upstream filter, a base model stage, and a downstream filter, and transforms a first aspect of the stream of tokens (e.g., disfluency, inverse text normalization (ITN), capitalization, etc.) from lexical form into display form. The upstream filter and/or the downstream filter alter the stream of tokens to change the default behavior of the DPP pipeline into custom behavior. Additional transformation stages of the DPP pipeline perform further transforms, allowing for outputting final text in a display format that is customized for a specific user. This permits each user to efficiently leverage a common baseline DPP pipeline to produce a custom output.</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZDBxDg0O8fdVcPEMDvBxjFQI8A8OUQgI8nd2DQ729HNX8PRTCA5wdXX2UAhydfZ39_MM8fT342FgTUvMKU7lhdLcDMpuriHOHrqpBfnxqcUFicmpeakl8aHBRgZGJiYGxqbGlo6GxsSpAgCFFCiT</recordid><startdate>20241205</startdate><enddate>20241205</enddate><creator>RAHMEL, Heiko Willy</creator><creator>CHANG, Shuangyu</creator><creator>ZHAO, Che</creator><creator>BEHRE, Piyush</creator><creator>KIBRE, Nicholas</creator><creator>SHAHID, Khuram</creator><creator>VARADHARAJAN, Padma</creator><creator>LIN, Edward C</creator><creator>LIU, Wei</creator><scope>EVB</scope></search><sort><creationdate>20241205</creationdate><title>CUSTOM DISPLAY POST PROCESSING IN SPEECH RECOGNITION</title><author>RAHMEL, Heiko Willy ; CHANG, Shuangyu ; ZHAO, Che ; BEHRE, Piyush ; KIBRE, Nicholas ; SHAHID, Khuram ; VARADHARAJAN, Padma ; LIN, Edward C ; LIU, Wei</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2024403539A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>RAHMEL, Heiko Willy</creatorcontrib><creatorcontrib>CHANG, Shuangyu</creatorcontrib><creatorcontrib>ZHAO, Che</creatorcontrib><creatorcontrib>BEHRE, Piyush</creatorcontrib><creatorcontrib>KIBRE, Nicholas</creatorcontrib><creatorcontrib>SHAHID, Khuram</creatorcontrib><creatorcontrib>VARADHARAJAN, Padma</creatorcontrib><creatorcontrib>LIN, Edward C</creatorcontrib><creatorcontrib>LIU, Wei</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>RAHMEL, Heiko Willy</au><au>CHANG, Shuangyu</au><au>ZHAO, Che</au><au>BEHRE, Piyush</au><au>KIBRE, Nicholas</au><au>SHAHID, Khuram</au><au>VARADHARAJAN, Padma</au><au>LIN, Edward C</au><au>LIU, Wei</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>CUSTOM DISPLAY POST PROCESSING IN SPEECH RECOGNITION</title><date>2024-12-05</date><risdate>2024</risdate><abstract>Solutions for custom display post processing (DPP) in speech recognition (SR) use a customized multi-stage DPP pipeline that transforms a stream of SR tokens from lexical form to display form. A first transformation stage of the DPP pipeline receives the stream of tokens, in turn, by an upstream filter, a base model stage, and a downstream filter, and transforms a first aspect of the stream of tokens (e.g., disfluency, inverse text normalization (ITN), capitalization, etc.) from lexical form into display form. The upstream filter and/or the downstream filter alter the stream of tokens to change the default behavior of the DPP pipeline into custom behavior. Additional transformation stages of the DPP pipeline perform further transforms, allowing for outputting final text in a display format that is customized for a specific user. This permits each user to efficiently leverage a common baseline DPP pipeline to produce a custom output.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US2024403539A1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | CUSTOM DISPLAY POST PROCESSING IN SPEECH RECOGNITION |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-23T16%3A18%3A42IST&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=RAHMEL,%20Heiko%20Willy&rft.date=2024-12-05&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2024403539A1%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 |