Coding Speech through Vocal Tract Kinematics

Guardado en:
Bibliografiske detaljer
Udgivet i:arXiv.org (Dec 14, 2024), p. n/a
Hovedforfatter: Cho, Cheol Jun
Andre forfattere: Wu, Peter, Prabhune, Tejas S, Agarwal, Dhruv, Anumanchipalli, Gopala K
Udgivet:
Cornell University Library, arXiv.org
Fag:
Online adgang:Citation/Abstract
Full text outside of ProQuest
Tags: Tilføj Tag
Ingen Tags, Vær først til at tagge denne postø!

MARC

LEADER 00000nab a2200000uu 4500
001 3070857631
003 UK-CbPIL
022 |a 2331-8422 
035 |a 3070857631 
045 0 |b d20241214 
100 1 |a Cho, Cheol Jun 
245 1 |a Coding Speech through Vocal Tract Kinematics 
260 |b Cornell University Library, arXiv.org  |c Dec 14, 2024 
513 |a Working Paper 
520 3 |a Vocal tract articulation is a natural, grounded control space of speech production. The spatiotemporal coordination of articulators combined with the vocal source shapes intelligible speech sounds to enable effective spoken communication. Based on this physiological grounding of speech, we propose a new framework of neural encoding-decoding of speech -- Speech Articulatory Coding (SPARC). SPARC comprises an articulatory analysis model that infers articulatory features from speech audio, and an articulatory synthesis model that synthesizes speech audio from articulatory features. The articulatory features are kinematic traces of vocal tract articulators and source features, which are intuitively interpretable and controllable, being the actual physical interface of speech production. An additional speaker identity encoder is jointly trained with the articulatory synthesizer to inform the voice texture of individual speakers. By training on large-scale speech data, we achieve a fully intelligible, high-quality articulatory synthesizer that generalizes to unseen speakers. Furthermore, the speaker embedding is effectively disentangled from articulations, which enables accent-perserving zero-shot voice conversion. To the best of our knowledge, this is the first demonstration of universal, high-performance articulatory inference and synthesis, suggesting the proposed framework as a powerful coding system of speech. 
653 |a Speech sounds 
653 |a Controllability 
653 |a Encoding-Decoding 
653 |a Codec 
653 |a Vocal tract 
653 |a Synthesis 
653 |a Speech 
653 |a Kinematics 
653 |a Articulation (speech) 
700 1 |a Wu, Peter 
700 1 |a Prabhune, Tejas S 
700 1 |a Agarwal, Dhruv 
700 1 |a Anumanchipalli, Gopala K 
773 0 |t arXiv.org  |g (Dec 14, 2024), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3070857631/abstract/embedded/ZKJTFFSVAI7CB62C?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/2406.12998