Transcribing code-switched bilingual lectures using deep neural networks with unit merging in acoustic modeling

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.