Minimum word error training of long short-term memory recurrent neural network language models for speech recognition

Takaaki Hori; Chiori Hori; Shinji Watanabe; John R. Hershey

doi:10.1109/ICASSP.2016.7472827

Minimum word error training of long short-term memory recurrent neural network language models for speech recognition

Takaaki Hori, Chiori Hori, Shinji Watanabe, John R. Hershey

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

10 Citations (Scopus)

Abstract

This paper describes minimum word error (MWE) training of recurrent neural network language models (RNNLMs) for speech recognition. RNNLMs are usually trained to minimize a cross entropy of estimated word probabilities against the correct word sequence, which corresponds to maximum likelihood criterion. However, this training does not necessarily maximize a performance measure in a target task, i.e. it does not minimize word error rate (WER) explicitly in speech recognition. To solve such a problem, several discriminative training methods have already been proposed for n-gram language models, but those for RNNLMs have not sufficiently investigated. In this paper, we propose a MWE training method for RNNLMs, and report significant WER reductions when we applied the MWE method to a standard Elman-type RNNLM and a more advanced model, a Long Short-Term Memory (LSTM) RNNLM. We also present efficient MWE training with N-best lists on Graphics Processing Units (GPUs).

Original language	English
Title of host publication	2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	5990-5994
Number of pages	5
Volume	2016-May
ISBN (Electronic)	9781479999880
DOIs	https://doi.org/10.1109/ICASSP.2016.7472827
Publication status	Published - 2016 May 18
Externally published	Yes
Event	41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Shanghai, China Duration: 2016 Mar 20 → 2016 Mar 25

Other

Other	41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016
Country/Territory	China
City	Shanghai
Period	16/3/20 → 16/3/25

Keywords

Long short-term memory
Minimum word error training
Recurrent neural network language model
Speech recognition

ASJC Scopus subject areas

Signal Processing
Software
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP.2016.7472827

Cite this

Hori, T., Hori, C., Watanabe, S., & Hershey, J. R. (2016). Minimum word error training of long short-term memory recurrent neural network language models for speech recognition. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings (Vol. 2016-May, pp. 5990-5994). [7472827] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2016.7472827

Minimum word error training of long short-term memory recurrent neural network language models for speech recognition. / Hori, Takaaki; Hori, Chiori; Watanabe, Shinji; Hershey, John R.

2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Vol. 2016-May Institute of Electrical and Electronics Engineers Inc., 2016. p. 5990-5994 7472827.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Hori, T, Hori, C, Watanabe, S & Hershey, JR 2016, Minimum word error training of long short-term memory recurrent neural network language models for speech recognition. in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. vol. 2016-May, 7472827, Institute of Electrical and Electronics Engineers Inc., pp. 5990-5994, 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, 16/3/20. https://doi.org/10.1109/ICASSP.2016.7472827

Hori T, Hori C, Watanabe S, Hershey JR. Minimum word error training of long short-term memory recurrent neural network language models for speech recognition. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Vol. 2016-May. Institute of Electrical and Electronics Engineers Inc. 2016. p. 5990-5994. 7472827 https://doi.org/10.1109/ICASSP.2016.7472827

Hori, Takaaki ; Hori, Chiori ; Watanabe, Shinji ; Hershey, John R. / Minimum word error training of long short-term memory recurrent neural network language models for speech recognition. 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Vol. 2016-May Institute of Electrical and Electronics Engineers Inc., 2016. pp. 5990-5994

@inproceedings{e3788215a524469986aab74d37ec79f5,

title = "Minimum word error training of long short-term memory recurrent neural network language models for speech recognition",

abstract = "This paper describes minimum word error (MWE) training of recurrent neural network language models (RNNLMs) for speech recognition. RNNLMs are usually trained to minimize a cross entropy of estimated word probabilities against the correct word sequence, which corresponds to maximum likelihood criterion. However, this training does not necessarily maximize a performance measure in a target task, i.e. it does not minimize word error rate (WER) explicitly in speech recognition. To solve such a problem, several discriminative training methods have already been proposed for n-gram language models, but those for RNNLMs have not sufficiently investigated. In this paper, we propose a MWE training method for RNNLMs, and report significant WER reductions when we applied the MWE method to a standard Elman-type RNNLM and a more advanced model, a Long Short-Term Memory (LSTM) RNNLM. We also present efficient MWE training with N-best lists on Graphics Processing Units (GPUs).",

keywords = "Long short-term memory, Minimum word error training, Recurrent neural network language model, Speech recognition",

author = "Takaaki Hori and Chiori Hori and Shinji Watanabe and Hershey, {John R.}",

year = "2016",

month = may,

day = "18",

doi = "10.1109/ICASSP.2016.7472827",

language = "English",

volume = "2016-May",

pages = "5990--5994",

booktitle = "2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 ; Conference date: 20-03-2016 Through 25-03-2016",

}

TY - GEN

T1 - Minimum word error training of long short-term memory recurrent neural network language models for speech recognition

AU - Hori, Takaaki

AU - Hori, Chiori

AU - Watanabe, Shinji

AU - Hershey, John R.

PY - 2016/5/18

Y1 - 2016/5/18

N2 - This paper describes minimum word error (MWE) training of recurrent neural network language models (RNNLMs) for speech recognition. RNNLMs are usually trained to minimize a cross entropy of estimated word probabilities against the correct word sequence, which corresponds to maximum likelihood criterion. However, this training does not necessarily maximize a performance measure in a target task, i.e. it does not minimize word error rate (WER) explicitly in speech recognition. To solve such a problem, several discriminative training methods have already been proposed for n-gram language models, but those for RNNLMs have not sufficiently investigated. In this paper, we propose a MWE training method for RNNLMs, and report significant WER reductions when we applied the MWE method to a standard Elman-type RNNLM and a more advanced model, a Long Short-Term Memory (LSTM) RNNLM. We also present efficient MWE training with N-best lists on Graphics Processing Units (GPUs).

AB - This paper describes minimum word error (MWE) training of recurrent neural network language models (RNNLMs) for speech recognition. RNNLMs are usually trained to minimize a cross entropy of estimated word probabilities against the correct word sequence, which corresponds to maximum likelihood criterion. However, this training does not necessarily maximize a performance measure in a target task, i.e. it does not minimize word error rate (WER) explicitly in speech recognition. To solve such a problem, several discriminative training methods have already been proposed for n-gram language models, but those for RNNLMs have not sufficiently investigated. In this paper, we propose a MWE training method for RNNLMs, and report significant WER reductions when we applied the MWE method to a standard Elman-type RNNLM and a more advanced model, a Long Short-Term Memory (LSTM) RNNLM. We also present efficient MWE training with N-best lists on Graphics Processing Units (GPUs).

KW - Long short-term memory

KW - Minimum word error training

KW - Recurrent neural network language model

KW - Speech recognition

UR - http://www.scopus.com/inward/record.url?scp=84973341477&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84973341477&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2016.7472827

DO - 10.1109/ICASSP.2016.7472827

M3 - Conference contribution

AN - SCOPUS:84973341477

VL - 2016-May

SP - 5990

EP - 5994

BT - 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016

Y2 - 20 March 2016 through 25 March 2016

ER -

Minimum word error training of long short-term memory recurrent neural network language models for speech recognition

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this