A trainable Vietnamese speech synthesis system based on HMM

This paper describes an approach to the realization of a trainable speech synthesis system using a technique whereby speech is directly synthesized from Hidden Markov models (HMMs), and apply it to the Vietnamese synthesis system. A series of data should be prepared before the training and synthesis...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Linyu He, Jian Yang, Libo Zuo, Liping Kui
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 3913
container_issue
container_start_page 3910
container_title
container_volume
creator Linyu He
Jian Yang
Libo Zuo
Liping Kui
description This paper describes an approach to the realization of a trainable speech synthesis system using a technique whereby speech is directly synthesized from Hidden Markov models (HMMs), and apply it to the Vietnamese synthesis system. A series of data should be prepared before the training and synthesis process, including the collection of data, recording, labelling, the design of contextual property and problem sets. The whole training and synthesis process is based on the HMM based Speech Synthesis System-2.0 (HTS-2.0) and it is automated. The final synthesis result shows that using this method to the Vietnamese synthesis system is feasible.
doi_str_mv 10.1109/ICEICE.2011.5777589
format Conference Proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_5777589</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5777589</ieee_id><sourcerecordid>5777589</sourcerecordid><originalsourceid>FETCH-ieee_primary_57775893</originalsourceid><addsrcrecordid>eNp9jj0LwjAYhCMi-NVf0CV_wJr0I2lwklKpQzdxLam-0kgbS98s_fd2KLh5HNxz3HKE-JwFnDN1vGb55CBknAeJlDJJ1YJseRzGccoiJZa_IviaeIhvNkkIxSXbkNOZukEbq-sW6N2As7oDBIo9wKOhOFrXABqcCB10tNYIT_qxtCjLPVm9dIvgzbkj_iW_ZcXBAEDVD6bTw1jNp6L_6xdzfTlF</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>A trainable Vietnamese speech synthesis system based on HMM</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Linyu He ; Jian Yang ; Libo Zuo ; Liping Kui</creator><creatorcontrib>Linyu He ; Jian Yang ; Libo Zuo ; Liping Kui</creatorcontrib><description>This paper describes an approach to the realization of a trainable speech synthesis system using a technique whereby speech is directly synthesized from Hidden Markov models (HMMs), and apply it to the Vietnamese synthesis system. A series of data should be prepared before the training and synthesis process, including the collection of data, recording, labelling, the design of contextual property and problem sets. The whole training and synthesis process is based on the HMM based Speech Synthesis System-2.0 (HTS-2.0) and it is automated. The final synthesis result shows that using this method to the Vietnamese synthesis system is feasible.</description><identifier>ISBN: 1424480361</identifier><identifier>ISBN: 9781424480364</identifier><identifier>EISBN: 1424480396</identifier><identifier>EISBN: 1424480388</identifier><identifier>EISBN: 9781424480395</identifier><identifier>EISBN: 9781424480388</identifier><identifier>DOI: 10.1109/ICEICE.2011.5777589</identifier><language>eng</language><publisher>IEEE</publisher><subject>Hidden Markov models ; Information processing ; Phase change materials ; Smoothing methods ; Speech ; Speech synthesis ; Training ; Vietnamese</subject><ispartof>2011 International Conference on Electric Information and Control Engineering, 2011, p.3910-3913</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/5777589$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2051,27904,54899</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5777589$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Linyu He</creatorcontrib><creatorcontrib>Jian Yang</creatorcontrib><creatorcontrib>Libo Zuo</creatorcontrib><creatorcontrib>Liping Kui</creatorcontrib><title>A trainable Vietnamese speech synthesis system based on HMM</title><title>2011 International Conference on Electric Information and Control Engineering</title><addtitle>ICEICE</addtitle><description>This paper describes an approach to the realization of a trainable speech synthesis system using a technique whereby speech is directly synthesized from Hidden Markov models (HMMs), and apply it to the Vietnamese synthesis system. A series of data should be prepared before the training and synthesis process, including the collection of data, recording, labelling, the design of contextual property and problem sets. The whole training and synthesis process is based on the HMM based Speech Synthesis System-2.0 (HTS-2.0) and it is automated. The final synthesis result shows that using this method to the Vietnamese synthesis system is feasible.</description><subject>Hidden Markov models</subject><subject>Information processing</subject><subject>Phase change materials</subject><subject>Smoothing methods</subject><subject>Speech</subject><subject>Speech synthesis</subject><subject>Training</subject><subject>Vietnamese</subject><isbn>1424480361</isbn><isbn>9781424480364</isbn><isbn>1424480396</isbn><isbn>1424480388</isbn><isbn>9781424480395</isbn><isbn>9781424480388</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2011</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNp9jj0LwjAYhCMi-NVf0CV_wJr0I2lwklKpQzdxLam-0kgbS98s_fd2KLh5HNxz3HKE-JwFnDN1vGb55CBknAeJlDJJ1YJseRzGccoiJZa_IviaeIhvNkkIxSXbkNOZukEbq-sW6N2As7oDBIo9wKOhOFrXABqcCB10tNYIT_qxtCjLPVm9dIvgzbkj_iW_ZcXBAEDVD6bTw1jNp6L_6xdzfTlF</recordid><startdate>201104</startdate><enddate>201104</enddate><creator>Linyu He</creator><creator>Jian Yang</creator><creator>Libo Zuo</creator><creator>Liping Kui</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201104</creationdate><title>A trainable Vietnamese speech synthesis system based on HMM</title><author>Linyu He ; Jian Yang ; Libo Zuo ; Liping Kui</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-ieee_primary_57775893</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Hidden Markov models</topic><topic>Information processing</topic><topic>Phase change materials</topic><topic>Smoothing methods</topic><topic>Speech</topic><topic>Speech synthesis</topic><topic>Training</topic><topic>Vietnamese</topic><toplevel>online_resources</toplevel><creatorcontrib>Linyu He</creatorcontrib><creatorcontrib>Jian Yang</creatorcontrib><creatorcontrib>Libo Zuo</creatorcontrib><creatorcontrib>Liping Kui</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</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>Linyu He</au><au>Jian Yang</au><au>Libo Zuo</au><au>Liping Kui</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>A trainable Vietnamese speech synthesis system based on HMM</atitle><btitle>2011 International Conference on Electric Information and Control Engineering</btitle><stitle>ICEICE</stitle><date>2011-04</date><risdate>2011</risdate><spage>3910</spage><epage>3913</epage><pages>3910-3913</pages><isbn>1424480361</isbn><isbn>9781424480364</isbn><eisbn>1424480396</eisbn><eisbn>1424480388</eisbn><eisbn>9781424480395</eisbn><eisbn>9781424480388</eisbn><abstract>This paper describes an approach to the realization of a trainable speech synthesis system using a technique whereby speech is directly synthesized from Hidden Markov models (HMMs), and apply it to the Vietnamese synthesis system. A series of data should be prepared before the training and synthesis process, including the collection of data, recording, labelling, the design of contextual property and problem sets. The whole training and synthesis process is based on the HMM based Speech Synthesis System-2.0 (HTS-2.0) and it is automated. The final synthesis result shows that using this method to the Vietnamese synthesis system is feasible.</abstract><pub>IEEE</pub><doi>10.1109/ICEICE.2011.5777589</doi></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 1424480361
ispartof 2011 International Conference on Electric Information and Control Engineering, 2011, p.3910-3913
issn
language eng
recordid cdi_ieee_primary_5777589
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Hidden Markov models
Information processing
Phase change materials
Smoothing methods
Speech
Speech synthesis
Training
Vietnamese
title A trainable Vietnamese speech synthesis system based on HMM
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-22T20%3A16%3A18IST&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=A%20trainable%20Vietnamese%20speech%20synthesis%20system%20based%20on%20HMM&rft.btitle=2011%20International%20Conference%20on%20Electric%20Information%20and%20Control%20Engineering&rft.au=Linyu%20He&rft.date=2011-04&rft.spage=3910&rft.epage=3913&rft.pages=3910-3913&rft.isbn=1424480361&rft.isbn_list=9781424480364&rft_id=info:doi/10.1109/ICEICE.2011.5777589&rft_dat=%3Cieee_6IE%3E5777589%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=1424480396&rft.eisbn_list=1424480388&rft.eisbn_list=9781424480395&rft.eisbn_list=9781424480388&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=5777589&rfr_iscdi=true