Topic tracking language model for speech recognition

Authors:
Shinji Watanabe;Tomoharu Iwata;Takaaki Hori;Atsushi Sako;Yasuo Ariki
Affiliations:
NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0237, Japan;NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0237, Japan;NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0237, Japan;Graduate School of Engineering, Kobe University, 1-1, Rokkodai-cho, Nada-ku, Kobe 657-8501, Japan;Graduate School of Engineering, Kobe University, 1-1, Rokkodai-cho, Nada-ku, Kobe 657-8501, Japan
Venue:
Computer Speech and Language
Year:
2011

Citing 11
Cited 3

A Cache-Based Natural Language Model for Speech Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Task Adaptation Using MAP Estimation in N-Gram Language Modeling

ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97)-Volume 2 - Volume 2
Latent dirichlet allocation

The Journal of Machine Learning Research
Dynamic topic models

ICML '06 Proceedings of the 23rd international conference on Machine learning
Topic modeling: beyond bag-of-words

ICML '06 Proceedings of the 23rd international conference on Machine learning
Language Modeling Using PLSA-Based Topic HMM

IEICE - Transactions on Information and Systems
Style & topic language model adaptation using HMM-LDA

EMNLP '06 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing
Global models of document structure using latent permutations

NAACL '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Dynamic mixture models for multiple time series

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Topic tracking model for analyzing consumer purchase behavior

IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
Online multiscale dynamic topic models

Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining

Sequential Modeling of Topic Dynamics with Multiple Timescales

ACM Transactions on Knowledge Discovery from Data (TKDD)
Influence relation estimation based on lexical entrainment in conversation

Speech Communication
Semantic spaces for improving language modeling

Computer Speech and Language

Quantified Score

Hi-index	0.00

Visualization

Abstract

In a real environment, acoustic and language features often vary depending on the speakers, speaking styles and topic changes. To accommodate these changes, speech recognition approaches that include the incremental tracking of changing environments have attracted attention. This paper proposes a topic tracking language model that can adaptively track changes in topics based on current text information and previously estimated topic models in an on-line manner. The proposed model is applied to language model adaptation in speech recognition. We use the MIT OpenCourseWare corpus and Corpus of Spontaneous Japanese in speech recognition experiments, and show the effectiveness of the proposed method.