LANGUAGE MODEL LEARNING DEVICE, INTERACTION DEVICE, AND TRAINED LANGUAGE MODEL

LANGUAGE MODEL LEARNING DEVICE, INTERACTION DEVICE, AND TRAINED LANGUAGE MODEL

To provide a language model learning device by which a large-scale language model can be learned with low computational cost independent of speech synthesis and speech recognition performance.SOLUTION: The language model learning device includes: conversion means for converting text of a natural lan...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: MIZUNO JUNTA, OTAKE KIYOTAKA, ASAO YOSHIHIKO, TORISAWA KENTARO, OH JONG HOON
Format: Patent
Sprache:eng ; jpn
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 MIZUNO JUNTA
OTAKE KIYOTAKA
ASAO YOSHIHIKO
TORISAWA KENTARO
OH JONG HOON
description To provide a language model learning device by which a large-scale language model can be learned with low computational cost independent of speech synthesis and speech recognition performance.SOLUTION: The language model learning device includes: conversion means for converting text of a natural language to output a symbol string of phonetic symbols; and learning means for performing learning of a language model using the text and the symbol string outputted by the conversion means.SELECTED DRAWING: Figure 2 【課題】音声合成及び音声認識の性能とは独立で、低い計算コストで大規模言語モデルの学習が行える言語モデル学習装置を提供する。【解決手段】言語モデル学習装置は、自然言語のテキストを変換して表音記号の記号列を出力するための変換手段と、テキストと、変換手段により出力された記号列とを用いて、言語モデルの学習を行うための学習手段とを含む。【選択図】図２
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_JP2023125311A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>JP2023125311A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_JP2023125311A3</originalsourceid><addsrcrecordid>eNrjZPDzcfRzD3V0d1Xw9Xdx9VHwcXUM8vP0c1dwcQ3zdHbVUfD0C3ENcnQO8fT3g4s5-rkohAQ5evq5uiig6udhYE1LzClO5YXS3AxKbq4hzh66qQX58anFBYnJqXmpJfFeAUYGRsaGRqbGhoaOxkQpAgAk5S49</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>LANGUAGE MODEL LEARNING DEVICE, INTERACTION DEVICE, AND TRAINED LANGUAGE MODEL</title><source>esp@cenet</source><creator>MIZUNO JUNTA ; OTAKE KIYOTAKA ; ASAO YOSHIHIKO ; TORISAWA KENTARO ; OH JONG HOON</creator><creatorcontrib>MIZUNO JUNTA ; OTAKE KIYOTAKA ; ASAO YOSHIHIKO ; TORISAWA KENTARO ; OH JONG HOON</creatorcontrib><description>To provide a language model learning device by which a large-scale language model can be learned with low computational cost independent of speech synthesis and speech recognition performance.SOLUTION: The language model learning device includes: conversion means for converting text of a natural language to output a symbol string of phonetic symbols; and learning means for performing learning of a language model using the text and the symbol string outputted by the conversion means.SELECTED DRAWING: Figure 2 【課題】音声合成及び音声認識の性能とは独立で、低い計算コストで大規模言語モデルの学習が行える言語モデル学習装置を提供する。【解決手段】言語モデル学習装置は、自然言語のテキストを変換して表音記号の記号列を出力するための変換手段と、テキストと、変換手段により出力された記号列とを用いて、言語モデルの学習を行うための学習手段とを含む。【選択図】図２</description><language>eng ; jpn</language><subject>ACOUSTICS ; 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&amp;date=20230907&amp;DB=EPODOC&amp;CC=JP&amp;NR=2023125311A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230907&amp;DB=EPODOC&amp;CC=JP&amp;NR=2023125311A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>MIZUNO JUNTA</creatorcontrib><creatorcontrib>OTAKE KIYOTAKA</creatorcontrib><creatorcontrib>ASAO YOSHIHIKO</creatorcontrib><creatorcontrib>TORISAWA KENTARO</creatorcontrib><creatorcontrib>OH JONG HOON</creatorcontrib><title>LANGUAGE MODEL LEARNING DEVICE, INTERACTION DEVICE, AND TRAINED LANGUAGE MODEL</title><description>To provide a language model learning device by which a large-scale language model can be learned with low computational cost independent of speech synthesis and speech recognition performance.SOLUTION: The language model learning device includes: conversion means for converting text of a natural language to output a symbol string of phonetic symbols; and learning means for performing learning of a language model using the text and the symbol string outputted by the conversion means.SELECTED DRAWING: Figure 2 【課題】音声合成及び音声認識の性能とは独立で、低い計算コストで大規模言語モデルの学習が行える言語モデル学習装置を提供する。【解決手段】言語モデル学習装置は、自然言語のテキストを変換して表音記号の記号列を出力するための変換手段と、テキストと、変換手段により出力された記号列とを用いて、言語モデルの学習を行うための学習手段とを含む。【選択図】図２</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>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZPDzcfRzD3V0d1Xw9Xdx9VHwcXUM8vP0c1dwcQ3zdHbVUfD0C3ENcnQO8fT3g4s5-rkohAQ5evq5uiig6udhYE1LzClO5YXS3AxKbq4hzh66qQX58anFBYnJqXmpJfFeAUYGRsaGRqbGhoaOxkQpAgAk5S49</recordid><startdate>20230907</startdate><enddate>20230907</enddate><creator>MIZUNO JUNTA</creator><creator>OTAKE KIYOTAKA</creator><creator>ASAO YOSHIHIKO</creator><creator>TORISAWA KENTARO</creator><creator>OH JONG HOON</creator><scope>EVB</scope></search><sort><creationdate>20230907</creationdate><title>LANGUAGE MODEL LEARNING DEVICE, INTERACTION DEVICE, AND TRAINED LANGUAGE MODEL</title><author>MIZUNO JUNTA ; OTAKE KIYOTAKA ; ASAO YOSHIHIKO ; TORISAWA KENTARO ; OH JONG HOON</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_JP2023125311A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; jpn</language><creationdate>2023</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>MIZUNO JUNTA</creatorcontrib><creatorcontrib>OTAKE KIYOTAKA</creatorcontrib><creatorcontrib>ASAO YOSHIHIKO</creatorcontrib><creatorcontrib>TORISAWA KENTARO</creatorcontrib><creatorcontrib>OH JONG HOON</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>MIZUNO JUNTA</au><au>OTAKE KIYOTAKA</au><au>ASAO YOSHIHIKO</au><au>TORISAWA KENTARO</au><au>OH JONG HOON</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>LANGUAGE MODEL LEARNING DEVICE, INTERACTION DEVICE, AND TRAINED LANGUAGE MODEL</title><date>2023-09-07</date><risdate>2023</risdate><abstract>To provide a language model learning device by which a large-scale language model can be learned with low computational cost independent of speech synthesis and speech recognition performance.SOLUTION: The language model learning device includes: conversion means for converting text of a natural language to output a symbol string of phonetic symbols; and learning means for performing learning of a language model using the text and the symbol string outputted by the conversion means.SELECTED DRAWING: Figure 2 【課題】音声合成及び音声認識の性能とは独立で、低い計算コストで大規模言語モデルの学習が行える言語モデル学習装置を提供する。【解決手段】言語モデル学習装置は、自然言語のテキストを変換して表音記号の記号列を出力するための変換手段と、テキストと、変換手段により出力された記号列とを用いて、言語モデルの学習を行うための学習手段とを含む。【選択図】図２</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng ; jpn
recordid cdi_epo_espacenet_JP2023125311A
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 LANGUAGE MODEL LEARNING DEVICE, INTERACTION DEVICE, AND TRAINED LANGUAGE MODEL
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-06T23%3A16%3A32IST&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=MIZUNO%20JUNTA&rft.date=2023-09-07&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EJP2023125311A%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