https://scholars.lib.ntu.edu.tw/handle/123456789/580913
Title: | Semi-supervised learning for multi-speaker text-to-speech synthesis using discrete speech representation | Authors: | Tu T Chen Y.-J Liu A.H HUNG-YI LEE |
Keywords: | Speech communication; Speech synthesis; Data collection process; Encoder-decoder; High quality; Semi-supervised; Speaker characteristics; Speech data; Text-to-speech system; TTS systems; Semi-supervised learning | Issue Date: | 2020 | Journal Volume: | 2020-October | Start page/Pages: | 3191-3195 | Source: | Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH | Abstract: | Recently, end-to-end multi-speaker text-to-speech (TTS) systems gain success in the situation where a lot of high-quality speech plus their corresponding transcriptions are available. However, laborious paired data collection processes prevent many institutes from building multi-speaker TTS systems of great performance. In this work, we propose a semi-supervised learning approach for multi-speaker TTS. A multi-speaker TTS model can learn from the untranscribed audio via the proposed encoder-decoder framework with discrete speech representation. The experiment results demonstrate that with only an hour of paired speech data, whether the paired data is from multiple speakers or a single speaker, the proposed model can generate intelligible speech in different voices. We found the model can benefit from the proposed semi-supervised learning approach even when part of the unpaired speech data is noisy. In addition, our analysis reveals that different speaker characteristics of the paired data have an impact on the effectiveness of semi-supervised TTS. Copyright ? 2020 ISCA |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85098152714&doi=10.21437%2fInterspeech.2020-1824&partnerID=40&md5=48472c4b0d8ae99398db9d9cdb29e3fe https://scholars.lib.ntu.edu.tw/handle/123456789/580913 |
ISSN: | 2308457X | DOI: | 10.21437/Interspeech.2020-1824 |
Appears in Collections: | 電機工程學系 |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.