CASIA OpenIR  > 数字内容技术与服务研究中心  > 听觉模型与认知计算
A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese
Shiyu Zhou1,2; Linhao Dong1,2; Shuang Xu1; Bo Xu1
2018
Conference NameICONIP
Source PublicationICONIP
Issue2018
Conference Date2018
Conference PlaceSiem Reap, Cambodia
Abstract

The choice of modeling units is critical to automatic speech
recognition (ASR) tasks. Conventional ASR systems typically choose
context-dependent states (CD-states) or context-dependent phonemes
(CD-phonemes) as their modeling units. However, it has been challenged
by sequence-to-sequence attention-based models. On English ASR
tasks, previous attempts have already shown that the modeling unit of
graphemes can outperform that of phonemes by sequence-to-sequence
attention-based model. In this paper, we are concerned with modeling
units on Mandarin Chinese ASR tasks using sequence-to-sequence
attention-based models with the Transformer. Five modeling units are
explored including context-independent phonemes (CI-phonemes), syllables,
words, sub-words and characters. Experiments on HKUST datasets
demonstrate that the lexicon free modeling units can outperform lexicon
related modeling units in terms of character error rate (CER). Among
five modeling units, character based model performs best and establishes
a new state-of-the-art CER of 26.64% on HKUST datasets.

KeywordAsr Multi-head Attention Modeling Units Sequence-to-sequence Transformer
MOST Discipline Catalogue工学::计算机科学与技术(可授工学、理学学位)
Indexed ByEI
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/22393
Collection数字内容技术与服务研究中心_听觉模型与认知计算
Corresponding AuthorShiyu Zhou
Affiliation1.Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Shiyu Zhou,Linhao Dong,Shuang Xu,et al. A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese[C],2018.
Files in This Item: Download All
File Name/Size DocType Version Access License
A Comparison of Mode(335KB)会议 开放获取GNU GPLView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Shiyu Zhou]'s Articles
[Linhao Dong]'s Articles
[Shuang Xu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Shiyu Zhou]'s Articles
[Linhao Dong]'s Articles
[Shuang Xu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Shiyu Zhou]'s Articles
[Linhao Dong]'s Articles
[Shuang Xu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese.release.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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