Word-level Permutation and Improved Lower Frame Rate for RNN-Based Acoustic Modeling

CORC > 自动化研究所 > 中国科学院自动化研究所 > 数字内容技术与服务研究中心 > 听觉模型与认知计算

	Word-level Permutation and Improved Lower Frame Rate for RNN-Based Acoustic Modeling
	Yuanyuan Zhao1,2 ; Shiyu Zhou1,2 ; Shuang Xu1 ; Bo Xu 1
	2017
会议日期	November 14-18, 2017
会议地点	Guangzhou, China
关键词	Rnn-based Acoustic Model Acoustic Trajectory Lower Frame Rate Word-level Permutation
页码	859-869
英文摘要	Recently, the RNN-based acoustic model has shown promising performance. However, its generalization ability to multiple scenarios is not powerful enough for two reasons. Firstly, it encodes inter-word dependency, which conflicts with the nature that an acoustic model should model the pronunciation of words only. Secondly, the RNN-based acoustic model depicting the inner-word acoustic trajectory frame-by-frame is too precise to tolerate small distortions. In this work, we propose two variants to address aforementioned two problems. One is the word-level permutation, i.e. the order of input features and corresponding labels is shuffled with a proper probability according to word boundaries. It aims to eliminate inter-word dependencies. The other one is the improved LFR (iLFR) model, which equidistantly splits the original sentence into N utterances to overcome the discarding data in LFR model. Results based on LSTM RNN demonstrate 7\% relative performance improvement by jointing the word-level permutation and iLFR.
会议录	iconip2017
语种	英语
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/15429]
专题	数字内容技术与服务研究中心_听觉模型与认知计算
通讯作者	Yuanyuan Zhao
作者单位	1.Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences
推荐引用方式 GB/T 7714	Yuanyuan Zhao,Shiyu Zhou,Shuang Xu,et al. Word-level Permutation and Improved Lower Frame Rate for RNN-Based Acoustic Modeling[C]. 见:. Guangzhou, China. November 14-18, 2017.