On the Effectiveness of Acoustic BPE in Decoder-Only TTS

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Bohan, Shen, Feiyu, Guo, Yiwei, Wang, Shuai, Chen, Xie, Yu, Kai
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913566749097984
author Li, Bohan
Shen, Feiyu
Guo, Yiwei
Wang, Shuai
Chen, Xie
Yu, Kai
author_facet Li, Bohan
Shen, Feiyu
Guo, Yiwei
Wang, Shuai
Chen, Xie
Yu, Kai
contents Discretizing speech into tokens and generating them by a decoder-only model have been a promising direction for text-to-speech (TTS) and spoken language modeling (SLM). To shorten the sequence length of speech tokens, acoustic byte-pair encoding (BPE) has emerged in SLM that treats speech tokens from self-supervised semantic representations as characters to further compress the token sequence. But the gain in TTS has not been fully investigated, and the proper choice of acoustic BPE remains unclear. In this work, we conduct a comprehensive study on various settings of acoustic BPE to explore its effectiveness in decoder-only TTS models with semantic speech tokens. Experiments on LibriTTS verify that acoustic BPE uniformly increases the intelligibility and diversity of synthesized speech, while showing different features across BPE settings. Hence, acoustic BPE is a favorable tool for decoder-only TTS.
format Preprint
id arxiv_https___arxiv_org_abs_2407_03892
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle On the Effectiveness of Acoustic BPE in Decoder-Only TTS
Li, Bohan
Shen, Feiyu
Guo, Yiwei
Wang, Shuai
Chen, Xie
Yu, Kai
Sound
Artificial Intelligence
Audio and Speech Processing
Discretizing speech into tokens and generating them by a decoder-only model have been a promising direction for text-to-speech (TTS) and spoken language modeling (SLM). To shorten the sequence length of speech tokens, acoustic byte-pair encoding (BPE) has emerged in SLM that treats speech tokens from self-supervised semantic representations as characters to further compress the token sequence. But the gain in TTS has not been fully investigated, and the proper choice of acoustic BPE remains unclear. In this work, we conduct a comprehensive study on various settings of acoustic BPE to explore its effectiveness in decoder-only TTS models with semantic speech tokens. Experiments on LibriTTS verify that acoustic BPE uniformly increases the intelligibility and diversity of synthesized speech, while showing different features across BPE settings. Hence, acoustic BPE is a favorable tool for decoder-only TTS.
title On the Effectiveness of Acoustic BPE in Decoder-Only TTS
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2407.03892