For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Latent Words Recurrent Neural Network Language Models for Automatic Speech Recognition
Ryo MASUMURA Taichi ASAMI Takanobu OBA Sumitaka SAKAUCHI Akinori ITO
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2019/12/01
Online ISSN: 1745-1361
Type of Manuscript: PAPER
Category: Speech and Hearing
latent words recurrent neural network language models, n-gram approximation, Viterbi approximation, automatic speech recognition,
Full Text: PDF>>
This paper demonstrates latent word recurrent neural network language models (LW-RNN-LMs) for enhancing automatic speech recognition (ASR). LW-RNN-LMs are constructed so as to pick up advantages in both recurrent neural network language models (RNN-LMs) and latent word language models (LW-LMs). The RNN-LMs can capture long-range context information and offer strong performance, and the LW-LMs are robust for out-of-domain tasks based on the latent word space modeling. However, the RNN-LMs cannot explicitly capture hidden relationships behind observed words since a concept of a latent variable space is not present. In addition, the LW-LMs cannot take into account long-range relationships between latent words. Our idea is to combine RNN-LM and LW-LM so as to compensate individual disadvantages. The LW-RNN-LMs can support both a latent variable space modeling as well as LW-LMs and a long-range relationship modeling as well as RNN-LMs at the same time. From the viewpoint of RNN-LMs, LW-RNN-LM can be considered as a soft class RNN-LM with a vast latent variable space. In contrast, from the viewpoint of LW-LMs, LW-RNN-LM can be considered as an LW-LM that uses the RNN structure for latent variable modeling instead of an n-gram structure. This paper also details a parameter inference method and two kinds of implementation methods, an n-gram approximation and a Viterbi approximation, for introducing the LW-LM to ASR. Our experiments show effectiveness of LW-RNN-LMs on a perplexity evaluation for the Penn Treebank corpus and an ASR evaluation for Japanese spontaneous speech tasks.