Recent studies have shown various kinds of recurrent neural networks (RNNs) are becoming powerful sequence models in speech related applications. Our previous work in detecting questions of Mandarin speech presents that gated recurrent unit (GRU) based RNN can achieve significantly better results. In this paper, we try to open the black box to find the correlations between inner architecture of GRU and phonetic features of question sentences. We find that both update gate and reset gate in GRU blocks react when people begin to pronounce a word. According to the reactions, experiments are conducted to show the behavior of GRU based question detection approach on three important factors, including keywords or special structure of questions, final particles and interrogative intonation. We also observe that update gate and reset gate don’t collaborate well on our dataset. Based on the asynchronous acts of update gate and reset gate in GRU, we adapt the structure of GRU block to our dataset and get further performance improvement in question detection task.
Cite as: Tang, Y., Wu, Z., Meng, H., Xu, M., Cai, L. (2016) Analysis on Gated Recurrent Unit Based Question Detection Approach. Proc. Interspeech 2016, 735-739, doi: 10.21437/Interspeech.2016-964
@inproceedings{tang16_interspeech,
author={Yaodong Tang and Zhiyong Wu and Helen Meng and Mingxing Xu and Lianhong Cai},
title={{Analysis on Gated Recurrent Unit Based Question Detection Approach}},
year=2016,
booktitle={Proc. Interspeech 2016},
pages={735--739},
doi={10.21437/Interspeech.2016-964}
}