Training method of homophonic lyric model and generating method and device of homophonic lyrics

Training method of homophonic lyric model and generating method and device of homophonic lyrics

The embodiment of the invention discloses a training method of a homophonic lyric model and a generating method and device of homophonic lyrics, which are used for the technical field of lyric processing, and the method comprises the following steps: based on a first phoneme sequence and a second ph...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: KONG LING, LIU CHENG, LIU SHUYI, PENG HUI, ZHAO WEIFENG, CHEN ZILAN, ZHU ZHOUYANG, WANG WUCHENG, LIU YANBIN, LI LEI
Format: Patent
Sprache:chi ; eng
Schlagworte:
CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
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 KONG LING
LIU CHENG
LIU SHUYI
PENG HUI
ZHAO WEIFENG
CHEN ZILAN
ZHU ZHOUYANG
WANG WUCHENG
LIU YANBIN
LI LEI
description The embodiment of the invention discloses a training method of a homophonic lyric model and a generating method and device of homophonic lyrics, which are used for the technical field of lyric processing, and the method comprises the following steps: based on a first phoneme sequence and a second phoneme sequence, determining an initial phoneme mapping relation of a song sample corresponding to a first pronunciation dictionary and a second pronunciation dictionary; and performing mutual verification on the initial phoneme mapping relationships corresponding to the song samples to obtain a target phoneme mapping relationship, and taking the target phoneme mapping relationship as a homophonic lyric model. By determining the phoneme mapping relation between the pronunciation dictionaries and taking the phoneme mapping relation between the pronunciation dictionaries as the homophonic lyric model, song lyrics corresponding to the first pronunciation dictionary can be converted into homophonic lyrics corresponding
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN117093851A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN117093851A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN117093851A3</originalsourceid><addsrcrecordid>eNrjZIgPKUrMzMvMS1fITS3JyE9RyE9TyMjPzS_IyM_LTFbIqSwCkrn5Kak5Col5KQrpqXmpRYklSOpBoimpZZnJqdi0FvMwsKYl5hSn8kJpbgZFN9cQZw_d1IL8-NTigsRkoIkl8c5-hobmBpbGFqaGjsbEqAEAhC49AA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Training method of homophonic lyric model and generating method and device of homophonic lyrics</title><source>esp@cenet</source><creator>KONG LING ; LIU CHENG ; LIU SHUYI ; PENG HUI ; ZHAO WEIFENG ; CHEN ZILAN ; ZHU ZHOUYANG ; WANG WUCHENG ; LIU YANBIN ; LI LEI</creator><creatorcontrib>KONG LING ; LIU CHENG ; LIU SHUYI ; PENG HUI ; ZHAO WEIFENG ; CHEN ZILAN ; ZHU ZHOUYANG ; WANG WUCHENG ; LIU YANBIN ; LI LEI</creatorcontrib><description>The embodiment of the invention discloses a training method of a homophonic lyric model and a generating method and device of homophonic lyrics, which are used for the technical field of lyric processing, and the method comprises the following steps: based on a first phoneme sequence and a second phoneme sequence, determining an initial phoneme mapping relation of a song sample corresponding to a first pronunciation dictionary and a second pronunciation dictionary; and performing mutual verification on the initial phoneme mapping relationships corresponding to the song samples to obtain a target phoneme mapping relationship, and taking the target phoneme mapping relationship as a homophonic lyric model. By determining the phoneme mapping relation between the pronunciation dictionaries and taking the phoneme mapping relation between the pronunciation dictionaries as the homophonic lyric model, song lyrics corresponding to the first pronunciation dictionary can be converted into homophonic lyrics corresponding</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</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=20231121&amp;DB=EPODOC&amp;CC=CN&amp;NR=117093851A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20231121&amp;DB=EPODOC&amp;CC=CN&amp;NR=117093851A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>KONG LING</creatorcontrib><creatorcontrib>LIU CHENG</creatorcontrib><creatorcontrib>LIU SHUYI</creatorcontrib><creatorcontrib>PENG HUI</creatorcontrib><creatorcontrib>ZHAO WEIFENG</creatorcontrib><creatorcontrib>CHEN ZILAN</creatorcontrib><creatorcontrib>ZHU ZHOUYANG</creatorcontrib><creatorcontrib>WANG WUCHENG</creatorcontrib><creatorcontrib>LIU YANBIN</creatorcontrib><creatorcontrib>LI LEI</creatorcontrib><title>Training method of homophonic lyric model and generating method and device of homophonic lyrics</title><description>The embodiment of the invention discloses a training method of a homophonic lyric model and a generating method and device of homophonic lyrics, which are used for the technical field of lyric processing, and the method comprises the following steps: based on a first phoneme sequence and a second phoneme sequence, determining an initial phoneme mapping relation of a song sample corresponding to a first pronunciation dictionary and a second pronunciation dictionary; and performing mutual verification on the initial phoneme mapping relationships corresponding to the song samples to obtain a target phoneme mapping relationship, and taking the target phoneme mapping relationship as a homophonic lyric model. By determining the phoneme mapping relation between the pronunciation dictionaries and taking the phoneme mapping relation between the pronunciation dictionaries as the homophonic lyric model, song lyrics corresponding to the first pronunciation dictionary can be converted into homophonic lyrics corresponding</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>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZIgPKUrMzMvMS1fITS3JyE9RyE9TyMjPzS_IyM_LTFbIqSwCkrn5Kak5Col5KQrpqXmpRYklSOpBoimpZZnJqdi0FvMwsKYl5hSn8kJpbgZFN9cQZw_d1IL8-NTigsRkoIkl8c5-hobmBpbGFqaGjsbEqAEAhC49AA</recordid><startdate>20231121</startdate><enddate>20231121</enddate><creator>KONG LING</creator><creator>LIU CHENG</creator><creator>LIU SHUYI</creator><creator>PENG HUI</creator><creator>ZHAO WEIFENG</creator><creator>CHEN ZILAN</creator><creator>ZHU ZHOUYANG</creator><creator>WANG WUCHENG</creator><creator>LIU YANBIN</creator><creator>LI LEI</creator><scope>EVB</scope></search><sort><creationdate>20231121</creationdate><title>Training method of homophonic lyric model and generating method and device of homophonic lyrics</title><author>KONG LING ; LIU CHENG ; LIU SHUYI ; PENG HUI ; ZHAO WEIFENG ; CHEN ZILAN ; ZHU ZHOUYANG ; WANG WUCHENG ; LIU YANBIN ; LI LEI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN117093851A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>KONG LING</creatorcontrib><creatorcontrib>LIU CHENG</creatorcontrib><creatorcontrib>LIU SHUYI</creatorcontrib><creatorcontrib>PENG HUI</creatorcontrib><creatorcontrib>ZHAO WEIFENG</creatorcontrib><creatorcontrib>CHEN ZILAN</creatorcontrib><creatorcontrib>ZHU ZHOUYANG</creatorcontrib><creatorcontrib>WANG WUCHENG</creatorcontrib><creatorcontrib>LIU YANBIN</creatorcontrib><creatorcontrib>LI LEI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>KONG LING</au><au>LIU CHENG</au><au>LIU SHUYI</au><au>PENG HUI</au><au>ZHAO WEIFENG</au><au>CHEN ZILAN</au><au>ZHU ZHOUYANG</au><au>WANG WUCHENG</au><au>LIU YANBIN</au><au>LI LEI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Training method of homophonic lyric model and generating method and device of homophonic lyrics</title><date>2023-11-21</date><risdate>2023</risdate><abstract>The embodiment of the invention discloses a training method of a homophonic lyric model and a generating method and device of homophonic lyrics, which are used for the technical field of lyric processing, and the method comprises the following steps: based on a first phoneme sequence and a second phoneme sequence, determining an initial phoneme mapping relation of a song sample corresponding to a first pronunciation dictionary and a second pronunciation dictionary; and performing mutual verification on the initial phoneme mapping relationships corresponding to the song samples to obtain a target phoneme mapping relationship, and taking the target phoneme mapping relationship as a homophonic lyric model. By determining the phoneme mapping relation between the pronunciation dictionaries and taking the phoneme mapping relation between the pronunciation dictionaries as the homophonic lyric model, song lyrics corresponding to the first pronunciation dictionary can be converted into homophonic lyrics corresponding</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN117093851A
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title Training method of homophonic lyric model and generating method and device of homophonic lyrics
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-29T13%3A45%3A36IST&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=KONG%20LING&rft.date=2023-11-21&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN117093851A%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