High Quality Sinusoidal Modeling of Wideband Speech for the Purposes of Speech Synthesis and Modification
This paper describes an efficient sinusoidal modeling framework for high quality wide band (WB) speech synthesis and modification. This technique may serve as a basis for speech compression in the context of small footprint concatenative Text to Speech systems. In addition, it is a useful representa...
Gespeichert in:
Hauptverfasser: | , , , , , , |
---|---|
Format: | Tagungsbericht |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | I |
---|---|
container_issue | |
container_start_page | I |
container_title | |
container_volume | 1 |
creator | Chazan, D. Hoory, R. Sagi, A. Shechtman, S. Sorin, A. Zhi Wei Shuang Bakis, R. |
description | This paper describes an efficient sinusoidal modeling framework for high quality wide band (WB) speech synthesis and modification. This technique may serve as a basis for speech compression in the context of small footprint concatenative Text to Speech systems. In addition, it is a useful representation for voice transformation and morphing purposes, e.g., simultaneous pitch modification and spectral envelope warping. The conventional sinusoidal modeling is enhanced with an adaptive frequency dithering mechanism, based on a degree of voicing analysis. Considerable reduction of the amount of model parameters is achieved by high band phase extension. The proposed model is evaluated and compared to the alternative STRAIGHT framework [1]. Being simpler and considerably more efficient than STRAIGHT, it outperforms it in speech quality for both speech reconstruction and transformation. |
doi_str_mv | 10.1109/ICASSP.2006.1660161 |
format | Conference Proceeding |
fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_1660161</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1660161</ieee_id><sourcerecordid>1660161</sourcerecordid><originalsourceid>FETCH-ieee_primary_16601613</originalsourceid><addsrcrecordid>eNp9j81Kw0AURgd_wKB5gm7mBRLvnYyTzlKKUhdCZQTdlbG5aa7ETMgki7y9LWTd1bc4hwOfECuEHBHs49vm2bldrgBMjsYAGrwSiSpKm6GF72uR2nKNWmkN2tj1jUjwSUFmUNs7kcb4CwBoTakLlQje8rGRH5NveZyl426KgSvfyvdQUcvdUYZafnFFP76rpOuJDo2swyDHhuRuGvoQKZ6dBbm5O5HIUZ79U4RrPviRQ_cgbmvfRkqXvRer15fPzTZjItr3A__5Yd4vh4rL9B_9jUyd</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>High Quality Sinusoidal Modeling of Wideband Speech for the Purposes of Speech Synthesis and Modification</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Chazan, D. ; Hoory, R. ; Sagi, A. ; Shechtman, S. ; Sorin, A. ; Zhi Wei Shuang ; Bakis, R.</creator><creatorcontrib>Chazan, D. ; Hoory, R. ; Sagi, A. ; Shechtman, S. ; Sorin, A. ; Zhi Wei Shuang ; Bakis, R.</creatorcontrib><description>This paper describes an efficient sinusoidal modeling framework for high quality wide band (WB) speech synthesis and modification. This technique may serve as a basis for speech compression in the context of small footprint concatenative Text to Speech systems. In addition, it is a useful representation for voice transformation and morphing purposes, e.g., simultaneous pitch modification and spectral envelope warping. The conventional sinusoidal modeling is enhanced with an adaptive frequency dithering mechanism, based on a degree of voicing analysis. Considerable reduction of the amount of model parameters is achieved by high band phase extension. The proposed model is evaluated and compared to the alternative STRAIGHT framework [1]. Being simpler and considerably more efficient than STRAIGHT, it outperforms it in speech quality for both speech reconstruction and transformation.</description><identifier>ISSN: 1520-6149</identifier><identifier>ISBN: 9781424404698</identifier><identifier>ISBN: 142440469X</identifier><identifier>EISSN: 2379-190X</identifier><identifier>DOI: 10.1109/ICASSP.2006.1660161</identifier><language>eng</language><publisher>IEEE</publisher><subject>Acoustic waves ; Frequency ; Laboratories ; Power harmonic filters ; Signal synthesis ; Speech analysis ; Speech coding ; Speech enhancement ; Speech synthesis ; Wideband</subject><ispartof>2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings, 2006, Vol.1, p.I-I</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/1660161$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,4050,4051,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1660161$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Chazan, D.</creatorcontrib><creatorcontrib>Hoory, R.</creatorcontrib><creatorcontrib>Sagi, A.</creatorcontrib><creatorcontrib>Shechtman, S.</creatorcontrib><creatorcontrib>Sorin, A.</creatorcontrib><creatorcontrib>Zhi Wei Shuang</creatorcontrib><creatorcontrib>Bakis, R.</creatorcontrib><title>High Quality Sinusoidal Modeling of Wideband Speech for the Purposes of Speech Synthesis and Modification</title><title>2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings</title><addtitle>ICASSP</addtitle><description>This paper describes an efficient sinusoidal modeling framework for high quality wide band (WB) speech synthesis and modification. This technique may serve as a basis for speech compression in the context of small footprint concatenative Text to Speech systems. In addition, it is a useful representation for voice transformation and morphing purposes, e.g., simultaneous pitch modification and spectral envelope warping. The conventional sinusoidal modeling is enhanced with an adaptive frequency dithering mechanism, based on a degree of voicing analysis. Considerable reduction of the amount of model parameters is achieved by high band phase extension. The proposed model is evaluated and compared to the alternative STRAIGHT framework [1]. Being simpler and considerably more efficient than STRAIGHT, it outperforms it in speech quality for both speech reconstruction and transformation.</description><subject>Acoustic waves</subject><subject>Frequency</subject><subject>Laboratories</subject><subject>Power harmonic filters</subject><subject>Signal synthesis</subject><subject>Speech analysis</subject><subject>Speech coding</subject><subject>Speech enhancement</subject><subject>Speech synthesis</subject><subject>Wideband</subject><issn>1520-6149</issn><issn>2379-190X</issn><isbn>9781424404698</isbn><isbn>142440469X</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2006</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNp9j81Kw0AURgd_wKB5gm7mBRLvnYyTzlKKUhdCZQTdlbG5aa7ETMgki7y9LWTd1bc4hwOfECuEHBHs49vm2bldrgBMjsYAGrwSiSpKm6GF72uR2nKNWmkN2tj1jUjwSUFmUNs7kcb4CwBoTakLlQje8rGRH5NveZyl426KgSvfyvdQUcvdUYZafnFFP76rpOuJDo2swyDHhuRuGvoQKZ6dBbm5O5HIUZ79U4RrPviRQ_cgbmvfRkqXvRer15fPzTZjItr3A__5Yd4vh4rL9B_9jUyd</recordid><startdate>2006</startdate><enddate>2006</enddate><creator>Chazan, D.</creator><creator>Hoory, R.</creator><creator>Sagi, A.</creator><creator>Shechtman, S.</creator><creator>Sorin, A.</creator><creator>Zhi Wei Shuang</creator><creator>Bakis, R.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>2006</creationdate><title>High Quality Sinusoidal Modeling of Wideband Speech for the Purposes of Speech Synthesis and Modification</title><author>Chazan, D. ; Hoory, R. ; Sagi, A. ; Shechtman, S. ; Sorin, A. ; Zhi Wei Shuang ; Bakis, R.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-ieee_primary_16601613</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2006</creationdate><topic>Acoustic waves</topic><topic>Frequency</topic><topic>Laboratories</topic><topic>Power harmonic filters</topic><topic>Signal synthesis</topic><topic>Speech analysis</topic><topic>Speech coding</topic><topic>Speech enhancement</topic><topic>Speech synthesis</topic><topic>Wideband</topic><toplevel>online_resources</toplevel><creatorcontrib>Chazan, D.</creatorcontrib><creatorcontrib>Hoory, R.</creatorcontrib><creatorcontrib>Sagi, A.</creatorcontrib><creatorcontrib>Shechtman, S.</creatorcontrib><creatorcontrib>Sorin, A.</creatorcontrib><creatorcontrib>Zhi Wei Shuang</creatorcontrib><creatorcontrib>Bakis, R.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Chazan, D.</au><au>Hoory, R.</au><au>Sagi, A.</au><au>Shechtman, S.</au><au>Sorin, A.</au><au>Zhi Wei Shuang</au><au>Bakis, R.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>High Quality Sinusoidal Modeling of Wideband Speech for the Purposes of Speech Synthesis and Modification</atitle><btitle>2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings</btitle><stitle>ICASSP</stitle><date>2006</date><risdate>2006</risdate><volume>1</volume><spage>I</spage><epage>I</epage><pages>I-I</pages><issn>1520-6149</issn><eissn>2379-190X</eissn><isbn>9781424404698</isbn><isbn>142440469X</isbn><abstract>This paper describes an efficient sinusoidal modeling framework for high quality wide band (WB) speech synthesis and modification. This technique may serve as a basis for speech compression in the context of small footprint concatenative Text to Speech systems. In addition, it is a useful representation for voice transformation and morphing purposes, e.g., simultaneous pitch modification and spectral envelope warping. The conventional sinusoidal modeling is enhanced with an adaptive frequency dithering mechanism, based on a degree of voicing analysis. Considerable reduction of the amount of model parameters is achieved by high band phase extension. The proposed model is evaluated and compared to the alternative STRAIGHT framework [1]. Being simpler and considerably more efficient than STRAIGHT, it outperforms it in speech quality for both speech reconstruction and transformation.</abstract><pub>IEEE</pub><doi>10.1109/ICASSP.2006.1660161</doi></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | ISSN: 1520-6149 |
ispartof | 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings, 2006, Vol.1, p.I-I |
issn | 1520-6149 2379-190X |
language | eng |
recordid | cdi_ieee_primary_1660161 |
source | IEEE Electronic Library (IEL) Conference Proceedings |
subjects | Acoustic waves Frequency Laboratories Power harmonic filters Signal synthesis Speech analysis Speech coding Speech enhancement Speech synthesis Wideband |
title | High Quality Sinusoidal Modeling of Wideband Speech for the Purposes of Speech Synthesis and Modification |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-06T07%3A02%3A56IST&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=High%20Quality%20Sinusoidal%20Modeling%20of%20Wideband%20Speech%20for%20the%20Purposes%20of%20Speech%20Synthesis%20and%20Modification&rft.btitle=2006%20IEEE%20International%20Conference%20on%20Acoustics%20Speech%20and%20Signal%20Processing%20Proceedings&rft.au=Chazan,%20D.&rft.date=2006&rft.volume=1&rft.spage=I&rft.epage=I&rft.pages=I-I&rft.issn=1520-6149&rft.eissn=2379-190X&rft.isbn=9781424404698&rft.isbn_list=142440469X&rft_id=info:doi/10.1109/ICASSP.2006.1660161&rft_dat=%3Cieee_6IE%3E1660161%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=1660161&rfr_iscdi=true |