Frame Stacking And Retaining For Recurrent Neural Network Acoustic Model

Abstract

Frame stacking is broadly applied in end-to-end neural network training like connectionist temporal classification (CTC), and it leads to more accurate models and faster decoding. However, it is not well-suited to conventional neural network based on context-dependent state acoustic model, if the decoder is unchanged. In this paper, we propose a novel frame retaining method which is applied in decoding. The system which combined frame retaining with frame stacking could reduces the time consumption of both training and decoding. Long short-term memory (LSTM) recurrent neural networks (RNNs) using it achieve almost linear training speedup and reduces relative 41% real time factor (RTF). At the same time, recognition performance is no degradation or improves sightly on Shenma voice search dataset in Mandarin.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keytian2017frame

Related papers

• Gated Recurrent Unit Based Acoustic Modeling With Future Context (2018)7.16
• Deep LSTM For Large Vocabulary Continuous Speech Recognition (2017)14.58
• Improved Neural Language Model Fusion For Streaming Recurrent Neural Network Transducer (2020)8.82
• Memory Visualization For Gated Recurrent Neural Networks In Speech Recognition (2016)11.76
• Mandarin Tone Modeling Using Recurrent Neural Networks (2017)0.00
• Exploring Architectures, Data And Units For Streaming End-to-end Speech Recognition With Rnn-transducer (2018)16.21
• High Order Recurrent Neural Networks For Acoustic Modelling (2018)8.60
• Speech Separation Using An Asynchronous Fully Recurrent Convolutional Neural Network (2021)0.00