Research on Acceleration Method of Speech Recognition Training

摘要：

　　Recurrent Neural Network(RNN)is now widely used in speech recognition.Experiments show that it has significant advantages over traditional methods,but complex computation limits its application,especially in real-time application scenarios.Recurrent neural network is heavily dependent on the pre and post-state in calculation process,and there is much overlap information,so overlapping information can be reduced to accelerate training.This paper construct a training acceleration structure,which reduces the computation cost and accelerates training speed by discarding the dependence of pre-and post state of RNN.Then correcting the recognition results errors with text corrector.We verify the proposed method on the TIMIT and Librispeech datasets,which prove that this approach achieves about 3 times speedup with little relative accuracy reduction.

关键词： Speech recognition Accelerating training Text correction

作者: Liang Bai Jingfei Jiang Yong Dou

作者单位: National University of Defense Technology,Changsha,China

会议类型: 国际会议

会议名称: the 12th Conference on Advanced Computer Architecture?(ACA 2018)(2018年全国计算机体系结构学术年会)

会议地点: 辽宁营口

会议语种:英文

页码: 42-50

在线出版日期: 2018-08-10（万方平台首次上网日期，不代表论文的发表时间）