中文版 | English
Title

SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing

Author
Corresponding AuthorZhou, Long
Publication Years
2022
Conference Name
60th Annual Meeting of the Association-for-Computational-Linguistics (ACL)
Source Title
Conference Date
MAY 22-27, 2022
Conference Place
null,Dublin,IRELAND
Publication Place
209 N EIGHTH STREET, STROUDSBURG, PA 18360 USA
Publisher
Abstract
Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural language processing models, we propose a unified-modal SpeechT5 framework that explores the encoder-decoder pre-training for self-supervised speech/text representation learning. The SpeechT5 framework consists of a shared encoder-decoder network and six modal-specific (speech/text) pre/post-nets. After preprocessing the input speech/text through the pre-nets, the shared encoder-decoder network models the sequence-to-sequence transformation, and then the post-nets generate the output in the speech/text modality based on the output of the decoder. Leveraging large-scale unlabeled speech and text data, we pre-train SpeechT5 to learn a unified-modal representation, hoping to improve the modeling capability for both speech and text. To align the textual and speech information into this unified semantic space, we propose a cross-modal vector quantization approach that randomly mixes up speech/text states with latent units as the interface between encoder and decoder. Extensive evaluations show the superiority of the proposed SpeechT5 framework on a wide variety of spoken language processing tasks, including automatic speech recognition, speech synthesis, speech translation, voice conversion, speech enhancement, and speaker identification.
SUSTech Authorship
First
Language
English
URL[Source Record]
Indexed By
WOS Research Area
Computer Science ; Linguistics
WOS Subject
Computer Science, Artificial Intelligence ; Computer Science, Interdisciplinary Applications ; Linguistics
WOS Accession No
WOS:000828702305058
Data Source
Web of Science
Citation statistics
Cited Times [WOS]:4
Document TypeConference paper
Identifierhttp://kc.sustech.edu.cn/handle/2SGJ60CL/401486
DepartmentDepartment of Computer Science and Engineering
Affiliation
1.Southern Univ Sci & Technol, Dept Comp Sci & Engn, Shenzhen, Peoples R China
2.Hong Kong Polytech Univ, Dept Comp, Hong Kong, Peoples R China
3.Tongji Univ, Dept Comp Sci & Technol, Shanghai, Peoples R China
4.Microsoft, Redmond, WA 98052 USA
5.Peng Cheng Lab, Shenzhen, Peoples R China
First Author AffilicationDepartment of Computer Science and Engineering
First Author's First AffilicationDepartment of Computer Science and Engineering
Recommended Citation
GB/T 7714
Ao, Junyi,Wang, Rui,Zhou, Long,et al. SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing[C]. 209 N EIGHTH STREET, STROUDSBURG, PA 18360 USA:ASSOC COMPUTATIONAL LINGUISTICS-ACL,2022.
Files in This Item:
There are no files associated with this item.
Related Services
Fulltext link
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Export to Excel
Export to Csv
Altmetrics Score
Google Scholar
Similar articles in Google Scholar
[Ao, Junyi]'s Articles
[Wang, Rui]'s Articles
[Zhou, Long]'s Articles
Baidu Scholar
Similar articles in Baidu Scholar
[Ao, Junyi]'s Articles
[Wang, Rui]'s Articles
[Zhou, Long]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Ao, Junyi]'s Articles
[Wang, Rui]'s Articles
[Zhou, Long]'s Articles
Terms of Use
No data!
Social Bookmark/Share
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.