Voice Puppetry with FastPitch

Emelie Van de Vreken; Korin Richmond; Catherine Lai

Voice Puppetry with FastPitch

Emelie Van de Vreken, Korin Richmond, Catherine Lai

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

Affective speech synthesis is an active research area, but recent approaches usually lack the full, fine-grained controllability to produce utterances with any exact affect intended by the user. We propose a puppetry tool based on FastPitch to help model output convey any required suprasegmental meanings. Users can choose any trained FastPitch model, and which features should be mimicked, making the approach fine-grained and language-independent.

Original language	English
Title of host publication	Proceedings of the Annual Conference of the International Speech Communication Association
Publisher	ISCA
Pages	5219-5220
Number of pages	2
Volume	2022-September
Publication status	Published - 22 Sept 2022
Event	Interspeech 2022 - Incheon, Korea, Republic of Duration: 18 Sept 2022 → 22 Sept 2022 Conference number: 23 https://interspeech2022.org/

Publication series

Name	Interspeech
Publisher	ISCA
ISSN (Electronic)	2308-457X

Conference

Conference	Interspeech 2022
Country/Territory	Korea, Republic of
City	Incheon
Period	18/09/22 → 22/09/22
Internet address	https://interspeech2022.org/

Keywords / Materials (for Non-textual outputs)

speech synthesis
voice puppetry

Access to Document

VanDeVrekenEtAl2022VoicePuppetryWithFastpitchAccepted author manuscript, 11.7 MBLicence: Creative Commons: Attribution (CC-BY)

https://www.isca-speech.org/archive/interspeech_2022/vandevreken22_interspeech.html

Cite this

@inproceedings{62c838ee86d047a69a35a6fd0f1c3b0f,

title = "Voice Puppetry with FastPitch",

abstract = "Affective speech synthesis is an active research area, but recent approaches usually lack the full, fine-grained controllability to produce utterances with any exact affect intended by the user. We propose a puppetry tool based on FastPitch to help model output convey any required suprasegmental meanings. Users can choose any trained FastPitch model, and which features should be mimicked, making the approach fine-grained and language-independent.",

keywords = "speech synthesis, voice puppetry",

author = "{Van de Vreken}, Emelie and Korin Richmond and Catherine Lai",

note = "Funding Information: This work was supported in part by the UKRI Centre for Doctoral Training in Natural Language Processing, funded by the UKRI (grant EP/S022481/1) and the University of Edinburgh, School of Informatics and School of Philosophy, Psychology & Language Sciences. ; Interspeech 2022 ; Conference date: 18-09-2022 Through 22-09-2022",

year = "2022",

month = sep,

day = "22",

language = "English",

volume = "2022-September",

series = "Interspeech",

publisher = "ISCA",

pages = "5219--5220",

booktitle = "Proceedings of the Annual Conference of the International Speech Communication Association",

url = "https://interspeech2022.org/",

}

TY - GEN

T1 - Voice Puppetry with FastPitch

AU - Van de Vreken, Emelie

AU - Richmond, Korin

AU - Lai, Catherine

N1 - Conference code: 23

PY - 2022/9/22

Y1 - 2022/9/22

N2 - Affective speech synthesis is an active research area, but recent approaches usually lack the full, fine-grained controllability to produce utterances with any exact affect intended by the user. We propose a puppetry tool based on FastPitch to help model output convey any required suprasegmental meanings. Users can choose any trained FastPitch model, and which features should be mimicked, making the approach fine-grained and language-independent.

AB - Affective speech synthesis is an active research area, but recent approaches usually lack the full, fine-grained controllability to produce utterances with any exact affect intended by the user. We propose a puppetry tool based on FastPitch to help model output convey any required suprasegmental meanings. Users can choose any trained FastPitch model, and which features should be mimicked, making the approach fine-grained and language-independent.

KW - speech synthesis

KW - voice puppetry

M3 - Conference contribution

VL - 2022-September

T3 - Interspeech

SP - 5219

EP - 5220

BT - Proceedings of the Annual Conference of the International Speech Communication Association

PB - ISCA

T2 - Interspeech 2022

Y2 - 18 September 2022 through 22 September 2022

ER -

Voice Puppetry with FastPitch

Abstract / Description of output

Publication series

Conference

Keywords / Materials (for Non-textual outputs)

Access to Document

Fingerprint

Cite this