Into-TTS : Intonation Template Based Prosody Control System
Intonations play an important role in delivering the intention of a speaker. However, current end-to-end TTS systems often fail to model proper intonations. To alleviate this problem, we propose a novel, intuitive method to synthesize speech in different intonations using predefined intonation templ...
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| 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 | Lee, Jihwan Lee, Joun Yeop Choi, Heejin Mun, Seongkyu Park, Sangjun Bae, Jae-Sung Kim, Chanwoo |
| description | Intonations play an important role in delivering the intention of a speaker.
However, current end-to-end TTS systems often fail to model proper intonations.
To alleviate this problem, we propose a novel, intuitive method to synthesize
speech in different intonations using predefined intonation templates. Prior to
TTS model training, speech data are grouped into intonation templates in an
unsupervised manner. Two proposed modules are added to the end-to-end TTS
framework: an intonation predictor and an intonation encoder. The intonation
predictor recommends a suitable intonation template to the given text. The
intonation encoder, attached to the text encoder output, synthesizes speech
abiding the requested intonation template. Main contributions of our paper are:
(a) an easy-to-use intonation control system covering a wide range of users;
(b) better performance in wrapping speech in a requested intonation with
improved objective and subjective evaluation; and (c) incorporating a
pre-trained language model for intonation modelling. Audio samples are
available at https://srtts.github.io/IntoTTS. |
| doi_str_mv | 10.48550/arxiv.2204.01271 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2204_01271</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2204_01271</sourcerecordid><originalsourceid>FETCH-LOGICAL-a671-769bfa8d3e47c50dbae34134976df64887fdeaff0b92c1b1005b1bc5ad2a2f873</originalsourceid><addsrcrecordid>eNotj7tqwzAYRrV0CGkfIFP1AnZ1teR2ak0vhkAC0W5-WRIYbCvIotRvX3KZzjcdvoPQjpJSaCnJC6S_4bdkjIiSUKboBr21c46FMSf8ii9zhjzEGRs_nUfIHn_A4h0-prhEt-ImzjnFEZ_WJfvpET0EGBf_dOcWma9P0_wU-8N327zvC6gULVRV2wDacS9UL4mz4LmgXNSqcqESWqvgPIRAbM16aikh0lLbS3AMWNCKb9HzTXt9353TMEFau0tFd63g_yDlQdY</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Into-TTS : Intonation Template Based Prosody Control System</title><source>arXiv.org</source><creator>Lee, Jihwan ; Lee, Joun Yeop ; Choi, Heejin ; Mun, Seongkyu ; Park, Sangjun ; Bae, Jae-Sung ; Kim, Chanwoo</creator><creatorcontrib>Lee, Jihwan ; Lee, Joun Yeop ; Choi, Heejin ; Mun, Seongkyu ; Park, Sangjun ; Bae, Jae-Sung ; Kim, Chanwoo</creatorcontrib><description>Intonations play an important role in delivering the intention of a speaker.
However, current end-to-end TTS systems often fail to model proper intonations.
To alleviate this problem, we propose a novel, intuitive method to synthesize
speech in different intonations using predefined intonation templates. Prior to
TTS model training, speech data are grouped into intonation templates in an
unsupervised manner. Two proposed modules are added to the end-to-end TTS
framework: an intonation predictor and an intonation encoder. The intonation
predictor recommends a suitable intonation template to the given text. The
intonation encoder, attached to the text encoder output, synthesizes speech
abiding the requested intonation template. Main contributions of our paper are:
(a) an easy-to-use intonation control system covering a wide range of users;
(b) better performance in wrapping speech in a requested intonation with
improved objective and subjective evaluation; and (c) incorporating a
pre-trained language model for intonation modelling. Audio samples are
available at https://srtts.github.io/IntoTTS.</description><identifier>DOI: 10.48550/arxiv.2204.01271</identifier><language>eng</language><subject>Computer Science - Learning ; Computer Science - Sound</subject><creationdate>2022-04</creationdate><rights>http://creativecommons.org/licenses/by-nc-nd/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2204.01271$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2204.01271$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Lee, Jihwan</creatorcontrib><creatorcontrib>Lee, Joun Yeop</creatorcontrib><creatorcontrib>Choi, Heejin</creatorcontrib><creatorcontrib>Mun, Seongkyu</creatorcontrib><creatorcontrib>Park, Sangjun</creatorcontrib><creatorcontrib>Bae, Jae-Sung</creatorcontrib><creatorcontrib>Kim, Chanwoo</creatorcontrib><title>Into-TTS : Intonation Template Based Prosody Control System</title><description>Intonations play an important role in delivering the intention of a speaker.
However, current end-to-end TTS systems often fail to model proper intonations.
To alleviate this problem, we propose a novel, intuitive method to synthesize
speech in different intonations using predefined intonation templates. Prior to
TTS model training, speech data are grouped into intonation templates in an
unsupervised manner. Two proposed modules are added to the end-to-end TTS
framework: an intonation predictor and an intonation encoder. The intonation
predictor recommends a suitable intonation template to the given text. The
intonation encoder, attached to the text encoder output, synthesizes speech
abiding the requested intonation template. Main contributions of our paper are:
(a) an easy-to-use intonation control system covering a wide range of users;
(b) better performance in wrapping speech in a requested intonation with
improved objective and subjective evaluation; and (c) incorporating a
pre-trained language model for intonation modelling. Audio samples are
available at https://srtts.github.io/IntoTTS.</description><subject>Computer Science - Learning</subject><subject>Computer Science - Sound</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj7tqwzAYRrV0CGkfIFP1AnZ1teR2ak0vhkAC0W5-WRIYbCvIotRvX3KZzjcdvoPQjpJSaCnJC6S_4bdkjIiSUKboBr21c46FMSf8ii9zhjzEGRs_nUfIHn_A4h0-prhEt-ImzjnFEZ_WJfvpET0EGBf_dOcWma9P0_wU-8N327zvC6gULVRV2wDacS9UL4mz4LmgXNSqcqESWqvgPIRAbM16aikh0lLbS3AMWNCKb9HzTXt9353TMEFau0tFd63g_yDlQdY</recordid><startdate>20220404</startdate><enddate>20220404</enddate><creator>Lee, Jihwan</creator><creator>Lee, Joun Yeop</creator><creator>Choi, Heejin</creator><creator>Mun, Seongkyu</creator><creator>Park, Sangjun</creator><creator>Bae, Jae-Sung</creator><creator>Kim, Chanwoo</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20220404</creationdate><title>Into-TTS : Intonation Template Based Prosody Control System</title><author>Lee, Jihwan ; Lee, Joun Yeop ; Choi, Heejin ; Mun, Seongkyu ; Park, Sangjun ; Bae, Jae-Sung ; Kim, Chanwoo</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a671-769bfa8d3e47c50dbae34134976df64887fdeaff0b92c1b1005b1bc5ad2a2f873</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Learning</topic><topic>Computer Science - Sound</topic><toplevel>online_resources</toplevel><creatorcontrib>Lee, Jihwan</creatorcontrib><creatorcontrib>Lee, Joun Yeop</creatorcontrib><creatorcontrib>Choi, Heejin</creatorcontrib><creatorcontrib>Mun, Seongkyu</creatorcontrib><creatorcontrib>Park, Sangjun</creatorcontrib><creatorcontrib>Bae, Jae-Sung</creatorcontrib><creatorcontrib>Kim, Chanwoo</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Lee, Jihwan</au><au>Lee, Joun Yeop</au><au>Choi, Heejin</au><au>Mun, Seongkyu</au><au>Park, Sangjun</au><au>Bae, Jae-Sung</au><au>Kim, Chanwoo</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Into-TTS : Intonation Template Based Prosody Control System</atitle><date>2022-04-04</date><risdate>2022</risdate><abstract>Intonations play an important role in delivering the intention of a speaker.
However, current end-to-end TTS systems often fail to model proper intonations.
To alleviate this problem, we propose a novel, intuitive method to synthesize
speech in different intonations using predefined intonation templates. Prior to
TTS model training, speech data are grouped into intonation templates in an
unsupervised manner. Two proposed modules are added to the end-to-end TTS
framework: an intonation predictor and an intonation encoder. The intonation
predictor recommends a suitable intonation template to the given text. The
intonation encoder, attached to the text encoder output, synthesizes speech
abiding the requested intonation template. Main contributions of our paper are:
(a) an easy-to-use intonation control system covering a wide range of users;
(b) better performance in wrapping speech in a requested intonation with
improved objective and subjective evaluation; and (c) incorporating a
pre-trained language model for intonation modelling. Audio samples are
available at https://srtts.github.io/IntoTTS.</abstract><doi>10.48550/arxiv.2204.01271</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.2204.01271 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_2204_01271 |
| source | arXiv.org |
| subjects | Computer Science - Learning Computer Science - Sound |
| title | Into-TTS : Intonation Template Based Prosody Control System |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-22T12%3A57%3A01IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Into-TTS%20:%20Intonation%20Template%20Based%20Prosody%20Control%20System&rft.au=Lee,%20Jihwan&rft.date=2022-04-04&rft_id=info:doi/10.48550/arxiv.2204.01271&rft_dat=%3Carxiv_GOX%3E2204_01271%3C/arxiv_GOX%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 |