Edinburgh Research Explorer

On training the recurrent neural network encoder-decoder for large vocabulary end-to-end speech recognition

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Related Edinburgh Organisations

Open Access permissions

Open

Documents

http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7472641
Original languageEnglish
Title of host publication2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages5060-5064
Number of pages5
ISBN (Electronic)978-1-4799-9988-0
ISBN (Print)978-1-4799-9987-3
DOIs
Publication statusPublished - Mar 2016
Event41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - China, Shanghai, China
Duration: 20 Mar 201625 Mar 2016
https://www2.securecms.com/ICASSP2016/Default.asp

Conference

Conference41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016
Abbreviated titleICASSP 2016
CountryChina
CityShanghai
Period20/03/1625/03/16
Internet address

Abstract

Recently, there has been an increasing interest in end-to-end speech recognition using neural networks, with no reliance on hidden Markov models (HMMs) for sequence modelling as in the standard hybrid framework. The recurrent neural network (RNN)
encoder-decoder is such a model, performing sequence to sequence mapping without any predefined alignment. This model first transforms the input sequence into a fixed length vector representation, from which the decoder recovers the output sequence. In this paper, we extend our previous work on this model for large vocabulary end-to-end speech recognition. We first present a more effective stochastic gradient decent (SGD) learning rate schedule that can significantly improve the recognition accuracy. We then extend the decoder with long memory by introducing another recurrent layer that performs implicit language modelling. Finally, we demonstrate that using multiple recurrent layers in the encoder can reduce the word error rate. Our experiments were carried out on the Switchboard corpus using a training set of around 300 hours of transcribed audio data, and we have achieved significantly higher recognition accuracy, thereby reduced the gap compared to the hybrid baseline.

Download statistics

No data available

ID: 23297508