Should you use a probabilistic duration model in TTS? Probably! Especially for spontaneous speech

Converting input symbols to output audio in TTS requires modelling the durations of speech sounds. Leading non-autoregressive (NAR) TTS models treat duration modelling as a regression problem. The same utterance is then spoken with identical timings every time, unlike when a human speaks. Probabilis...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Mehta, Shivam, Lameris, Harm, Punmiya, Rajiv, Beskow, Jonas, Székely, Éva, Henter, Gustav Eje
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 08.06.2024
Subjects
Modelling
Probabilistic models
Probability theory
Speech recognition
Speech sounds
Statistical analysis
Online AccessGet full text

Cover

More Information
Summary:Converting input symbols to output audio in TTS requires modelling the durations of speech sounds. Leading non-autoregressive (NAR) TTS models treat duration modelling as a regression problem. The same utterance is then spoken with identical timings every time, unlike when a human speaks. Probabilistic models of duration have been proposed, but there is mixed evidence of their benefits. However, prior studies generally only consider speech read aloud, and ignore spontaneous speech, despite the latter being both a more common and a more variable mode of speaking. We compare the effect of conventional deterministic duration modelling to durations sampled from a powerful probabilistic model based on conditional flow matching (OT-CFM), in three different NAR TTS approaches: regression-based, deep generative, and end-to-end. Across four different corpora, stochastic duration modelling improves probabilistic NAR TTS approaches, especially for spontaneous speech. Please see https://shivammehta25.github.io/prob_dur/ for audio and resources.
ISSN:2331-8422