Multilingual Prosody Transfer: Comparing Supervised & Transfer Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Goel, Arnav, Hira, Medha, Gupta, Anubha
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914837327511552
author Goel, Arnav
Hira, Medha
Gupta, Anubha
author_facet Goel, Arnav
Hira, Medha
Gupta, Anubha
contents The field of prosody transfer in speech synthesis systems is rapidly advancing. This research is focused on evaluating learning methods for adapting pre-trained monolingual text-to-speech (TTS) models to multilingual conditions, i.e., Supervised Fine-Tuning (SFT) and Transfer Learning (TL). This comparison utilizes three distinct metrics: Mean Opinion Score (MOS), Recognition Accuracy (RA), and Mel Cepstral Distortion (MCD). Results demonstrate that, in comparison to SFT, TL leads to significantly enhanced performance, with an average MOS higher by 1.53 points, a 37.5% increase in RA, and approximately a 7.8-point improvement in MCD. These findings are instrumental in helping build TTS models for low-resource languages.
format Preprint
id arxiv_https___arxiv_org_abs_2406_00022
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multilingual Prosody Transfer: Comparing Supervised & Transfer Learning
Goel, Arnav
Hira, Medha
Gupta, Anubha
Computation and Language
Sound
Audio and Speech Processing
The field of prosody transfer in speech synthesis systems is rapidly advancing. This research is focused on evaluating learning methods for adapting pre-trained monolingual text-to-speech (TTS) models to multilingual conditions, i.e., Supervised Fine-Tuning (SFT) and Transfer Learning (TL). This comparison utilizes three distinct metrics: Mean Opinion Score (MOS), Recognition Accuracy (RA), and Mel Cepstral Distortion (MCD). Results demonstrate that, in comparison to SFT, TL leads to significantly enhanced performance, with an average MOS higher by 1.53 points, a 37.5% increase in RA, and approximately a 7.8-point improvement in MCD. These findings are instrumental in helping build TTS models for low-resource languages.
title Multilingual Prosody Transfer: Comparing Supervised & Transfer Learning
topic Computation and Language
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2406.00022