Question detection from acoustic features using recurrent neural network with gated recurrent unit

Yaodong Tang, Yuchen Huang, Zhiyong Wu, Helen Meng, Mingxing Xu, Lianhong Cai
2016 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
Question detection is of importance for many speech applications. Only parts of the speech utterances can provide useful clues for question detection. Previous work of question detection using acoustic features in Mandarin conversation is weak in capturing such proper time context information, which could be modeled essentially in recurrent neural network (RNN) structure. In this paper, we conduct an investigation on recurrent approaches to cope with this problem. Based on gated recurrent unit
more » ... GRU), we build different RNN and bidirectional RNN (BRNN) models to extract efficient features at segment and utterance level. The particular advantage of GRU is it can determine a proper time scale to extract high-level contextual features. Experimental results show that the features extracted within proper time scale make the classifier perform better than the baseline method with pre-designed lexical and acoustic feature set. Index Terms-question detection, gated recurrent unit (GRU), bidirectional recurrent neural network (BRNN) 978-1-4799-9988-0/16/$31.00
doi:10.1109/icassp.2016.7472854 dblp:conf/icassp/TangHWMXC16 fatcat:2w44it2j3nccrkh5xvgvpjhtey