An Experimental Study on Vietnamese Speech Synthesis

The modern Vietnamese is a monosyllabic tone language. Each syllable can be marked with initial, final and tone. In this paper, Vietnamese speech synthesis system is realized by using a trainable HMM-based speech synthesis method. The basic synthesis units of this system are initials and finals. Acc...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liping Kui, Jian Yang, Bin He, Enxing Hu
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 235
container_issue
container_start_page 232
container_title
container_volume
creator Liping Kui
Jian Yang
Bin He
Enxing Hu
description The modern Vietnamese is a monosyllabic tone language. Each syllable can be marked with initial, final and tone. In this paper, Vietnamese speech synthesis system is realized by using a trainable HMM-based speech synthesis method. The basic synthesis units of this system are initials and finals. According to the characteristics of Vietnamese, we have conducted such works as collecting corpus, recording, labeling, determining the phonemes list, and designing context attributes and question set. Then Vietnamese speech synthesis system is constructed by using the STRAIGHT synthesizer under the HTS platform. At last, we conduct a subjective test to synthetic speech signals. The results of preliminary evaluation show that the intelligibility of the utterances is approximately 100%, and the quality of synthesis speech is from fair to good.
doi_str_mv 10.1109/IALP.2011.40
format Conference Proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6121510</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6121510</ieee_id><sourcerecordid>6121510</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-dd794a511525fc3ab044535787cd08dcb3ad63dfaedcbfad74a20ca1713d2a963</originalsourceid><addsrcrecordid>eNotjk1Lw0AURQekoNbs3LmZP5A4L_PxZpahVC0EFFLcltfMC420sXQimH9vRO_mHrhwuELcgyoAVHjcVPVbUSqAwqgrkQX0YCwioNZ-IW5_l6DRW3MtspQ-1BznPDp7I0w1yPX3mS_9iYeRjrIZv-IkPwf53vM40IkTy-bM3B5kMw3jgVOf7sSio2Pi7L-XYvu03q5e8vr1ebOq6rwPasxjxGDIAtjSdq2mvTLGaose26h8bPeaotOxI565o4iGStUSIOhYUnB6KR7-tD0z787zRbpMOwclWFD6B4h1RVU</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>An Experimental Study on Vietnamese Speech Synthesis</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Liping Kui ; Jian Yang ; Bin He ; Enxing Hu</creator><creatorcontrib>Liping Kui ; Jian Yang ; Bin He ; Enxing Hu</creatorcontrib><description>The modern Vietnamese is a monosyllabic tone language. Each syllable can be marked with initial, final and tone. In this paper, Vietnamese speech synthesis system is realized by using a trainable HMM-based speech synthesis method. The basic synthesis units of this system are initials and finals. According to the characteristics of Vietnamese, we have conducted such works as collecting corpus, recording, labeling, determining the phonemes list, and designing context attributes and question set. Then Vietnamese speech synthesis system is constructed by using the STRAIGHT synthesizer under the HTS platform. At last, we conduct a subjective test to synthetic speech signals. The results of preliminary evaluation show that the intelligibility of the utterances is approximately 100%, and the quality of synthesis speech is from fair to good.</description><identifier>ISBN: 9781457717338</identifier><identifier>ISBN: 1457717336</identifier><identifier>DOI: 10.1109/IALP.2011.40</identifier><identifier>LCCN: 2011937854</identifier><language>eng</language><publisher>IEEE</publisher><subject>basic synthesis units ; Context ; Hidden Markov models ; HMM-based ; Labeling ; Speech ; Speech synthesis ; STRAIGHT synthesizer ; Synthesizers ; Training ; Vietnamese</subject><ispartof>2011 International Conference on Asian Language Processing, 2011, p.232-235</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6121510$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2051,27904,54898</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6121510$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Liping Kui</creatorcontrib><creatorcontrib>Jian Yang</creatorcontrib><creatorcontrib>Bin He</creatorcontrib><creatorcontrib>Enxing Hu</creatorcontrib><title>An Experimental Study on Vietnamese Speech Synthesis</title><title>2011 International Conference on Asian Language Processing</title><addtitle>ialp</addtitle><description>The modern Vietnamese is a monosyllabic tone language. Each syllable can be marked with initial, final and tone. In this paper, Vietnamese speech synthesis system is realized by using a trainable HMM-based speech synthesis method. The basic synthesis units of this system are initials and finals. According to the characteristics of Vietnamese, we have conducted such works as collecting corpus, recording, labeling, determining the phonemes list, and designing context attributes and question set. Then Vietnamese speech synthesis system is constructed by using the STRAIGHT synthesizer under the HTS platform. At last, we conduct a subjective test to synthetic speech signals. The results of preliminary evaluation show that the intelligibility of the utterances is approximately 100%, and the quality of synthesis speech is from fair to good.</description><subject>basic synthesis units</subject><subject>Context</subject><subject>Hidden Markov models</subject><subject>HMM-based</subject><subject>Labeling</subject><subject>Speech</subject><subject>Speech synthesis</subject><subject>STRAIGHT synthesizer</subject><subject>Synthesizers</subject><subject>Training</subject><subject>Vietnamese</subject><isbn>9781457717338</isbn><isbn>1457717336</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2011</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotjk1Lw0AURQekoNbs3LmZP5A4L_PxZpahVC0EFFLcltfMC420sXQimH9vRO_mHrhwuELcgyoAVHjcVPVbUSqAwqgrkQX0YCwioNZ-IW5_l6DRW3MtspQ-1BznPDp7I0w1yPX3mS_9iYeRjrIZv-IkPwf53vM40IkTy-bM3B5kMw3jgVOf7sSio2Pi7L-XYvu03q5e8vr1ebOq6rwPasxjxGDIAtjSdq2mvTLGaose26h8bPeaotOxI565o4iGStUSIOhYUnB6KR7-tD0z787zRbpMOwclWFD6B4h1RVU</recordid><startdate>201111</startdate><enddate>201111</enddate><creator>Liping Kui</creator><creator>Jian Yang</creator><creator>Bin He</creator><creator>Enxing Hu</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201111</creationdate><title>An Experimental Study on Vietnamese Speech Synthesis</title><author>Liping Kui ; Jian Yang ; Bin He ; Enxing Hu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-dd794a511525fc3ab044535787cd08dcb3ad63dfaedcbfad74a20ca1713d2a963</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2011</creationdate><topic>basic synthesis units</topic><topic>Context</topic><topic>Hidden Markov models</topic><topic>HMM-based</topic><topic>Labeling</topic><topic>Speech</topic><topic>Speech synthesis</topic><topic>STRAIGHT synthesizer</topic><topic>Synthesizers</topic><topic>Training</topic><topic>Vietnamese</topic><toplevel>online_resources</toplevel><creatorcontrib>Liping Kui</creatorcontrib><creatorcontrib>Jian Yang</creatorcontrib><creatorcontrib>Bin He</creatorcontrib><creatorcontrib>Enxing Hu</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Liping Kui</au><au>Jian Yang</au><au>Bin He</au><au>Enxing Hu</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>An Experimental Study on Vietnamese Speech Synthesis</atitle><btitle>2011 International Conference on Asian Language Processing</btitle><stitle>ialp</stitle><date>2011-11</date><risdate>2011</risdate><spage>232</spage><epage>235</epage><pages>232-235</pages><isbn>9781457717338</isbn><isbn>1457717336</isbn><abstract>The modern Vietnamese is a monosyllabic tone language. Each syllable can be marked with initial, final and tone. In this paper, Vietnamese speech synthesis system is realized by using a trainable HMM-based speech synthesis method. The basic synthesis units of this system are initials and finals. According to the characteristics of Vietnamese, we have conducted such works as collecting corpus, recording, labeling, determining the phonemes list, and designing context attributes and question set. Then Vietnamese speech synthesis system is constructed by using the STRAIGHT synthesizer under the HTS platform. At last, we conduct a subjective test to synthetic speech signals. The results of preliminary evaluation show that the intelligibility of the utterances is approximately 100%, and the quality of synthesis speech is from fair to good.</abstract><pub>IEEE</pub><doi>10.1109/IALP.2011.40</doi><tpages>4</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 9781457717338
ispartof 2011 International Conference on Asian Language Processing, 2011, p.232-235
issn
language eng
recordid cdi_ieee_primary_6121510
source IEEE Electronic Library (IEL) Conference Proceedings
subjects basic synthesis units
Context
Hidden Markov models
HMM-based
Labeling
Speech
Speech synthesis
STRAIGHT synthesizer
Synthesizers
Training
Vietnamese
title An Experimental Study on Vietnamese Speech Synthesis
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-24T05%3A55%3A20IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=An%20Experimental%20Study%20on%20Vietnamese%20Speech%20Synthesis&rft.btitle=2011%20International%20Conference%20on%20Asian%20Language%20Processing&rft.au=Liping%20Kui&rft.date=2011-11&rft.spage=232&rft.epage=235&rft.pages=232-235&rft.isbn=9781457717338&rft.isbn_list=1457717336&rft_id=info:doi/10.1109/IALP.2011.40&rft_dat=%3Cieee_6IE%3E6121510%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6121510&rfr_iscdi=true