CUED Publications database

Recurrent neural network language model adaptation for multi-genre broadcast speech recognition

Chen, X and Tan, T and Liu, X and Lanchantin, P and Wan, M and Gales, MJF and Woodland, PC (2015) Recurrent neural network language model adaptation for multi-genre broadcast speech recognition. In: UNSPECIFIED pp. 3511-3515..

Full text not available from this repository.

Abstract

Copyright © 2015 ISCA. Recurrent neural network language models (RNNLMs) have recently become increasingly popular for many applications including speech recognition. In previous research RNNLMs have normally been trained on well-matched in-domain data. The adaptation of RNNLMs remains an open research area to be explored. In this paper, genre and topic based RNNLMadaptation techniques are investigated for a multi-genre broadcast transcription task. A number of techniques including Probabilistic Latent Semantic Analysis, Latent Dirichlet Allocation and Hierarchical Dirichlet Processes are used to extract show level topic information. These were then used as additional input to the RNNLM during training, which can facilitate unsupervised test time adaptation. Experiments using a state-of-theart LVCSR system trained on 1000 hours of speech and more than 1 billion words of text showed adaptation could yield perplexity reductions of 8% relatively over the baseline RNNLM and small but consistent word error rate reductions.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Subjects: UNSPECIFIED
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 19:01
Last Modified: 07 Sep 2017 01:47
DOI: