MODULAR DEEP LEARNING MODEL

The technology described herein uses a modular model to process speech. A deep learning based acoustic model comprises a stack of different types of neural network layers. The sub-modules of a deep learning based acoustic model can be used to represent distinct non-phonetic acoustic factors, such as...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	KUMAR Kshitiz, HUANG Yan, KALGAONKAR Kaustubh Prakash, GONG Yifan, LIU Chaojun
Format:	Patent
Sprache:	eng
Schlagworte:	ACOUSTICS MUSICAL INSTRUMENTS PHYSICS SPEECH ANALYSIS OR SYNTHESIS SPEECH OR AUDIO CODING OR DECODING SPEECH OR VOICE PROCESSING SPEECH RECOGNITION
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	KUMAR Kshitiz HUANG Yan KALGAONKAR Kaustubh Prakash GONG Yifan LIU Chaojun
description	The technology described herein uses a modular model to process speech. A deep learning based acoustic model comprises a stack of different types of neural network layers. The sub-modules of a deep learning based acoustic model can be used to represent distinct non-phonetic acoustic factors, such as accent origins (e.g. native, non-native), speech channels (e.g. mobile, bluetooth, desktop etc.), speech application scenario (e.g. voice search, short message dictation etc.), and speaker variation (e.g. individual speakers or clustered speakers), etc. The technology described herein uses certain sub-modules in a first context and a second group of sub-modules in a second context.
format	Patent
fullrecord	<record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2017256254A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2017256254A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2017256254A13</originalsourceid><addsrcrecordid>eNrjZJD29XcJ9XEMUnBxdQ1Q8HF1DPLz9HNXAIq6-vAwsKYl5hSn8kJpbgZlN9cQZw_d1IL8-NTigsTk1LzUkvjQYCMDQ3MjUzMjUxNHQ2PiVAEAwuUhTQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>MODULAR DEEP LEARNING MODEL</title><source>esp@cenet</source><creator>KUMAR Kshitiz ; HUANG Yan ; KALGAONKAR Kaustubh Prakash ; GONG Yifan ; LIU Chaojun</creator><creatorcontrib>KUMAR Kshitiz ; HUANG Yan ; KALGAONKAR Kaustubh Prakash ; GONG Yifan ; LIU Chaojun</creatorcontrib><description>The technology described herein uses a modular model to process speech. A deep learning based acoustic model comprises a stack of different types of neural network layers. The sub-modules of a deep learning based acoustic model can be used to represent distinct non-phonetic acoustic factors, such as accent origins (e.g. native, non-native), speech channels (e.g. mobile, bluetooth, desktop etc.), speech application scenario (e.g. voice search, short message dictation etc.), and speaker variation (e.g. individual speakers or clustered speakers), etc. The technology described herein uses certain sub-modules in a first context and a second group of sub-modules in a second context.</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>2017</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=20170907&DB=EPODOC&CC=US&NR=2017256254A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20170907&DB=EPODOC&CC=US&NR=2017256254A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>KUMAR Kshitiz</creatorcontrib><creatorcontrib>HUANG Yan</creatorcontrib><creatorcontrib>KALGAONKAR Kaustubh Prakash</creatorcontrib><creatorcontrib>GONG Yifan</creatorcontrib><creatorcontrib>LIU Chaojun</creatorcontrib><title>MODULAR DEEP LEARNING MODEL</title><description>The technology described herein uses a modular model to process speech. A deep learning based acoustic model comprises a stack of different types of neural network layers. The sub-modules of a deep learning based acoustic model can be used to represent distinct non-phonetic acoustic factors, such as accent origins (e.g. native, non-native), speech channels (e.g. mobile, bluetooth, desktop etc.), speech application scenario (e.g. voice search, short message dictation etc.), and speaker variation (e.g. individual speakers or clustered speakers), etc. The technology described herein uses certain sub-modules in a first context and a second group of sub-modules in a second context.</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>2017</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZJD29XcJ9XEMUnBxdQ1Q8HF1DPLz9HNXAIq6-vAwsKYl5hSn8kJpbgZlN9cQZw_d1IL8-NTigsTk1LzUkvjQYCMDQ3MjUzMjUxNHQ2PiVAEAwuUhTQ</recordid><startdate>20170907</startdate><enddate>20170907</enddate><creator>KUMAR Kshitiz</creator><creator>HUANG Yan</creator><creator>KALGAONKAR Kaustubh Prakash</creator><creator>GONG Yifan</creator><creator>LIU Chaojun</creator><scope>EVB</scope></search><sort><creationdate>20170907</creationdate><title>MODULAR DEEP LEARNING MODEL</title><author>KUMAR Kshitiz ; HUANG Yan ; KALGAONKAR Kaustubh Prakash ; GONG Yifan ; LIU Chaojun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2017256254A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2017</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>KUMAR Kshitiz</creatorcontrib><creatorcontrib>HUANG Yan</creatorcontrib><creatorcontrib>KALGAONKAR Kaustubh Prakash</creatorcontrib><creatorcontrib>GONG Yifan</creatorcontrib><creatorcontrib>LIU Chaojun</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>KUMAR Kshitiz</au><au>HUANG Yan</au><au>KALGAONKAR Kaustubh Prakash</au><au>GONG Yifan</au><au>LIU Chaojun</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>MODULAR DEEP LEARNING MODEL</title><date>2017-09-07</date><risdate>2017</risdate><abstract>The technology described herein uses a modular model to process speech. A deep learning based acoustic model comprises a stack of different types of neural network layers. The sub-modules of a deep learning based acoustic model can be used to represent distinct non-phonetic acoustic factors, such as accent origins (e.g. native, non-native), speech channels (e.g. mobile, bluetooth, desktop etc.), speech application scenario (e.g. voice search, short message dictation etc.), and speaker variation (e.g. individual speakers or clustered speakers), etc. The technology described herein uses certain sub-modules in a first context and a second group of sub-modules in a second context.</abstract><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier
ispartof
issn
language	eng
recordid	cdi_epo_espacenet_US2017256254A1
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	MODULAR DEEP LEARNING MODEL
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-02T03%3A37%3A00IST&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=KUMAR%20Kshitiz&rft.date=2017-09-07&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2017256254A1%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