Paper Info
Title
Transcribing code-switched bilingual lectures using deep neural networks with unit merging in acoustic modeling
Abstract
This paper considers the transcription of the widely observed yet less investigated bilingual code-switched speech: the words or phrases of the guest language are inserted within the utterances of the host language, so the languages are switched back and forth within an utterance, and much less data are available for the guest language. Two approaches utilizing the deep neural network (DNN) were tested and analyzed, including using DNN bottleneck features in HMM/GMM (BF-HMM/GMM) and modeling context-dependent HMM senones by DNN (CD-DNN-HMM). In both cases the unit merging (and recovery) techniques in acoustic modeling were used to handle the data imbalance problem. Improved recognition accuracies were observed with unit merging (and recovery) for the two approaches under different conditions.
Year
DOI
Venue
2014
10.1109/ICASSP.2014.6853590
ICASSP
Keywords
Field
DocType
deep neural networks,bf-hmm/gmm,acoustic modeling,unit merging,speech recognition,bilingual,data imbalance problem,host language,context-dependent hmm senones,code-switching,guest language,bilingual code-switched speech,code-switched bilingual lectures,hidden markov models,accuracy,merging,neural networks,acoustics,code switching,speech
Transcription (linguistics),Bottleneck,Computer science,Utterance,Speech recognition,Natural language processing,Data imbalance,Artificial intelligence,Artificial neural network,Hidden Markov model,Merge (version control),Deep neural networks
Conference
ISSN
Citations 
PageRank 
1520-6149
0
0.34
References 
Authors
11
2
Name
Order
Citations
PageRank
Ching-feng Yeh1716.88
Lin-shan Lee21525182.03