Sequence-Discriminative Training Of Deep Neural Networks
14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5(2013)
摘要
Sequence-discriminative training of deep neural networks (DNNs) is investigated on a 300 hour American English conversational telephone speech task. Different sequence discriminative criteria maximum mutual information (MMI), minimum phone error (MPE), state-level minimum Bayes risk (sMBR), and boosted MMI are compared. Two different heuristics are investigated to improve the performance of the DNNs trained using sequence-based criteria lattices are regenerated after the first iteration of training; and, for MMI and BMMI, the frames where the numerator and denominator hypotheses are disjoint are removed from the gradient computation. Starting from a competitive DNN baseline trained using cross-entropy, different sequence-discriminative criteria are shown to lower word error rates by 8-9% relative, on average. Little difference is noticed between the different sequence based criteria that are investigated. The experiments are done using the open-source Kaldi toolkit, which makes it possible for the wider community to reproduce these results.
更多查看译文
关键词
speech recognition,deep learning,sequence-criterion training,neural networks,reproducible research
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络