【11】Fast and accurate recurrent neural network acoustic models

【文件属性】：
文件名称：【11】Fast and accurate recurrent neural network acoustic models
文件大小：300KB
文件格式：PDF
更新时间：2022-09-15 04:44:02
学术论文 We have recently shown that deep Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) outperform feed forward deep neural networks (DNNs) as acoustic models for speech recognition. More recently, we have shown that the performance of sequence trained context dependent (CD) hidden Markov model (HMM) acoustic models using such LSTM RNNs can be equaled by sequence trained phone models initialized with connectionist temporal classification (CTC). In this paper, we present techniques that further improve performance of LSTM RNN acoustic models for large vocabulary speech recognition. We show that frame stacking and reduced frame rate lead to more accurate models and faster decoding. CD phone modeling leads to further improvements. We also present initial results for LSTM RNN models outputting words directly. Index Terms: speech recognition, acoustic modeling, connectionist temporal classification, CTC, long short-term memory recurrent neural networks, LSTM RNN.