DocumentCode :
3490401
Title :
A Phone Mapping Technique for Acoustic Modeling of Under-Resourced Languages
Author :
Van Hai Do ; Xiong Xiao ; Eng Siong Chng ; Haizhou Li
Author_Institution :
Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, Singapore
fYear :
2012
fDate :
13-15 Nov. 2012
Firstpage :
233
Lastpage :
236
Abstract :
This paper presents a novel method for acoustic modeling of a new language with a limited amount of training data. In this approach, we use well-trained acoustic models of a foreign language to generate acoustic scores for each feature vector of the target language. These scores are then used as the input for mapping to context dependent triphones of the target language using a limited amount of training data. With this approach, we do not need to modify or have a special requirement for the foreign acoustic models. In this paper, English is used as the foreign language while Malay is used as the target language. Experiments on a Malay large vocabulary continuous speech recognition (LVCSR) task show that with using only few minutes of training data we can achieve a low word error rate which outperforms the best monolingual baseline acoustic model significantly.
Keywords :
learning (artificial intelligence); natural language processing; speech recognition; English language; LVCSR task; Malay language; acoustic modeling; foreign language; large vocabulary continuous speech recognition task; monolingual baseline acoustic model; phone mapping technique; training data; under-resourced language; word error rate; Acoustics; Context modeling; Data models; Hidden Markov models; Speech; Speech recognition; Training data; LVCSR; cross-lingual; phone mapping; speech recognition; under-resourced language;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Asian Language Processing (IALP), 2012 International Conference on
Conference_Location :
Hanoi
Print_ISBN :
978-1-4673-6113-2
Electronic_ISBN :
978-0-7695-4886-9
Type :
conf
DOI :
10.1109/IALP.2012.17
Filename :
6473739
Link To Document :
بازگشت