Paper Info
Title
Acoustic modeling with a shared phoneme set for multilingual speech recognition without code-switching.
Abstract
This paper proposes a new acoustic modeling method for the automatic speech recognition (ASR) of data, in which multilingual utterances are mixed, without using any language identification technologies. To perform ASR of unknown language utterance, first, language identification is performed to determine the language. Then, a language-specific ASR system is used to recognize the utterance. Our proposed method does not train language-specific acoustic models but trains an acoustic model that can speech-recognize utterances spoken by some sort of language. To realize multilingual acoustic modeling, we create a new phoneme set by sharing a part of language-specific phonemes with other languages. The shared phoneme set enables the amount of training data to increase on appearance. Therefore, the acoustic model with the shared phoneme set can perform ASR for a minor language (low-resource language) utterance. The experimental result showed that the acoustic model with the shared phoneme set improved ASR performance for a few languages in comparison with the language-specific ASR system in which language identification was perfectly performed.
Year
Venue
Field
2017
Asia-Pacific Signal and Information Processing Association Annual Summit and Conference
Training set,Data modeling,Code-switching,Computer science,sort,Utterance,Speech recognition,Language identification,Hidden Markov model,Acoustic model
DocType
ISSN
Citations 
Conference
2309-9402
0
PageRank 
References 
Authors
0.34
0
2
Name
Order
Citations
PageRank
Shogo Hara100.34
Hiromitsu Nishizaki216329.49