Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

EXPLORING RETRAINING-FREE SPEECH RECOGNITION FOR INTRA-SENTENTIAL CODE-SWITCHING

Abstract: 

Code Switching refers to the phenomenon of changing languages within a sentence or discourse, and it represents a challenge for conventional automatic speech recognition systems deployed to tackle a single target language. The code switching problem is complicated by the lack of multi-lingual training data needed to build new and ad hoc multi-lingual acoustic and language models. In this work, we present a prototype research code-switching speech recognition system that leverages existing monolingual acoustic and language models, i.e., no ad hoc training is needed. To generate high quality pronunciation of foreign language words in the native language phoneme set, we use a combination of existing acoustic phone decoders and an LSTM-based grapheme-to-phoneme model. In addition, a code-switching language model was developed by using translated word pairs to borrow statistics from the native language model. We demonstrate that our approach handles accented foreign pronunciations better than techniques based on human labeling. Our best system reduces the WER from 34.4%, obtained with a conventional monolingual speech recognition system, to 15.3% on an intrasentential code-switching task, without harming the monolingual accuracy.

up
0 users have voted:

Paper Details

Authors:
Zhen Huang, Xiaodan Zhuang, Daben Liu, Xiaoqiang Xiao, Yuchen Zhang, Sabato Marco Siniscalchi
Submitted On:
7 May 2019 - 2:28pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Yuchen Zhang
Paper Code:
3409
Document Year:
2019
Cite

Document Files

CS_final-3 copy.pdf

(21)

Subscribe

[1] Zhen Huang, Xiaodan Zhuang, Daben Liu, Xiaoqiang Xiao, Yuchen Zhang, Sabato Marco Siniscalchi, "EXPLORING RETRAINING-FREE SPEECH RECOGNITION FOR INTRA-SENTENTIAL CODE-SWITCHING", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3942. Accessed: Jun. 25, 2019.
@article{3942-19,
url = {http://sigport.org/3942},
author = {Zhen Huang; Xiaodan Zhuang; Daben Liu; Xiaoqiang Xiao; Yuchen Zhang; Sabato Marco Siniscalchi },
publisher = {IEEE SigPort},
title = {EXPLORING RETRAINING-FREE SPEECH RECOGNITION FOR INTRA-SENTENTIAL CODE-SWITCHING},
year = {2019} }
TY - EJOUR
T1 - EXPLORING RETRAINING-FREE SPEECH RECOGNITION FOR INTRA-SENTENTIAL CODE-SWITCHING
AU - Zhen Huang; Xiaodan Zhuang; Daben Liu; Xiaoqiang Xiao; Yuchen Zhang; Sabato Marco Siniscalchi
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3942
ER -
Zhen Huang, Xiaodan Zhuang, Daben Liu, Xiaoqiang Xiao, Yuchen Zhang, Sabato Marco Siniscalchi. (2019). EXPLORING RETRAINING-FREE SPEECH RECOGNITION FOR INTRA-SENTENTIAL CODE-SWITCHING. IEEE SigPort. http://sigport.org/3942
Zhen Huang, Xiaodan Zhuang, Daben Liu, Xiaoqiang Xiao, Yuchen Zhang, Sabato Marco Siniscalchi, 2019. EXPLORING RETRAINING-FREE SPEECH RECOGNITION FOR INTRA-SENTENTIAL CODE-SWITCHING. Available at: http://sigport.org/3942.
Zhen Huang, Xiaodan Zhuang, Daben Liu, Xiaoqiang Xiao, Yuchen Zhang, Sabato Marco Siniscalchi. (2019). "EXPLORING RETRAINING-FREE SPEECH RECOGNITION FOR INTRA-SENTENTIAL CODE-SWITCHING." Web.
1. Zhen Huang, Xiaodan Zhuang, Daben Liu, Xiaoqiang Xiao, Yuchen Zhang, Sabato Marco Siniscalchi. EXPLORING RETRAINING-FREE SPEECH RECOGNITION FOR INTRA-SENTENTIAL CODE-SWITCHING [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3942