Single-stage TTS with Masked Audio Token Modeling and Semantic Knowledge Distillation

Gerard I. Gállego, Roy Fejgin, Chunghsin Yeh, Xiaoyu Liu, Gautam Bhattacharya
{"title":"Single-stage TTS with Masked Audio Token Modeling and Semantic Knowledge Distillation","authors":"Gerard I. Gállego, Roy Fejgin, Chunghsin Yeh, Xiaoyu Liu, Gautam Bhattacharya","doi":"arxiv-2409.11003","DOIUrl":null,"url":null,"abstract":"Audio token modeling has become a powerful framework for speech synthesis,\nwith two-stage approaches employing semantic tokens remaining prevalent. In\nthis paper, we aim to simplify this process by introducing a semantic knowledge\ndistillation method that enables high-quality speech generation in a single\nstage. Our proposed model improves speech quality, intelligibility, and speaker\nsimilarity compared to a single-stage baseline. Although two-stage systems\nstill lead in intelligibility, our model significantly narrows the gap while\ndelivering comparable speech quality. These findings showcase the potential of\nsingle-stage models to achieve efficient, high-quality TTS with a more compact\nand streamlined architecture.","PeriodicalId":501034,"journal":{"name":"arXiv - EE - Signal Processing","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - EE - Signal Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.11003","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Audio token modeling has become a powerful framework for speech synthesis, with two-stage approaches employing semantic tokens remaining prevalent. In this paper, we aim to simplify this process by introducing a semantic knowledge distillation method that enables high-quality speech generation in a single stage. Our proposed model improves speech quality, intelligibility, and speaker similarity compared to a single-stage baseline. Although two-stage systems still lead in intelligibility, our model significantly narrows the gap while delivering comparable speech quality. These findings showcase the potential of single-stage models to achieve efficient, high-quality TTS with a more compact and streamlined architecture.
采用屏蔽音频令牌建模和语义知识提炼技术的单级 TTS
音频标记建模已成为语音合成的一个强大框架,但采用语义标记的两阶段方法仍很普遍。在本文中,我们旨在通过引入一种语义知音发声方法来简化这一过程,从而在单阶段内生成高质量语音。与单级基线相比,我们提出的模型提高了语音质量、可懂度和说话人相似度。虽然两级系统在可懂度方面仍处于领先地位,但我们的模型大大缩小了差距,同时提供了相当的语音质量。这些发现展示了单级模型的潜力,它能以更紧凑、更精简的架构实现高效、高质量的 TTS。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信