Saved in:
Bibliographic Details
Main Authors: Guo, Yiwei, Wang, Chenrun, Yang, Yifan, Wang, Hankun, Ma, Ziyang, Du, Chenpeng, Wang, Shuai, Li, Hanzheng, Fan, Shuai, Zhang, Hui, Chen, Xie, Yu, Kai
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.06079
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911833935314944
author Guo, Yiwei
Wang, Chenrun
Yang, Yifan
Wang, Hankun
Ma, Ziyang
Du, Chenpeng
Wang, Shuai
Li, Hanzheng
Fan, Shuai
Zhang, Hui
Chen, Xie
Yu, Kai
author_facet Guo, Yiwei
Wang, Chenrun
Yang, Yifan
Wang, Hankun
Ma, Ziyang
Du, Chenpeng
Wang, Shuai
Li, Hanzheng
Fan, Shuai
Zhang, Hui
Chen, Xie
Yu, Kai
contents Discrete speech tokens have been more and more popular in multiple speech processing fields, including automatic speech recognition (ASR), text-to-speech (TTS) and singing voice synthesis (SVS). In this paper, we describe the systems developed by the SJTU X-LANCE group for the TTS (acoustic + vocoder), SVS, and ASR tracks in the Interspeech 2024 Speech Processing Using Discrete Speech Unit Challenge. Notably, we achieved 1st rank on the leaderboard in the TTS track both with the whole training set and only 1h training data, with the highest UTMOS score and lowest bitrate among all submissions.
format Preprint
id arxiv_https___arxiv_org_abs_2404_06079
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle The X-LANCE Technical Report for Interspeech 2024 Speech Processing Using Discrete Speech Unit Challenge
Guo, Yiwei
Wang, Chenrun
Yang, Yifan
Wang, Hankun
Ma, Ziyang
Du, Chenpeng
Wang, Shuai
Li, Hanzheng
Fan, Shuai
Zhang, Hui
Chen, Xie
Yu, Kai
Audio and Speech Processing
Artificial Intelligence
Discrete speech tokens have been more and more popular in multiple speech processing fields, including automatic speech recognition (ASR), text-to-speech (TTS) and singing voice synthesis (SVS). In this paper, we describe the systems developed by the SJTU X-LANCE group for the TTS (acoustic + vocoder), SVS, and ASR tracks in the Interspeech 2024 Speech Processing Using Discrete Speech Unit Challenge. Notably, we achieved 1st rank on the leaderboard in the TTS track both with the whole training set and only 1h training data, with the highest UTMOS score and lowest bitrate among all submissions.
title The X-LANCE Technical Report for Interspeech 2024 Speech Processing Using Discrete Speech Unit Challenge
topic Audio and Speech Processing
Artificial Intelligence
url https://arxiv.org/abs/2404.06079