Multi-Class Composite N-gram language model for spoken language processing using multiple word clusters

Authors:
Hirofumi Yamamoto;Shuntaro Isogai;Yoshinori Sagisaka
Affiliations:
ATR SLT, Soraku-gun, Kyoto-fu, Japan;Waseda University, Shinjuku-ku, Tokyo-to, Japan;GITI / ATR SLT, Shinjuku-ku, Tokyo-to, Japan
Venue:
ACL '01 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics
Year:
2001

Citing 4
Cited 3

Class-based n-gram models of natural language

Computational Linguistics
Spontaneous dialogue speech recognition using cross-word context constrained word graphs

ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 01
Variable-order N-gram generation by word-class splitting and consecutive word grouping

ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 01
Multi-class composite N-gram based on connection direction

ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01

Exploring asymmetric clustering for statistical language modeling

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Context dependent class language model based on word co-occurrence matrix in LSA framework for speech recognition

ACS'08 Proceedings of the 8th conference on Applied computer scince
Multi-speaker language modeling

HLT-NAACL-Short '04 Proceedings of HLT-NAACL 2004: Short Papers

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a new language model, the Multi-Class Composite N-gram, is proposed to avoid a data sparseness problem for spoken language in that it is difficult to collect training data. The Multi-Class Composite N-gram maintains an accurate word prediction capability and reliability for sparse data with a compact model size based on multiple word clusters, called Multi-Classes. In the Multi-Class, the statistical connectivity at each position of the N-grams is regarded as word attributes, and one word cluster each is created to represent the positional attributes. Furthermore, by introducing higher order word N-grams through the grouping of frequent word successions, Multi-Class N-grams are extended to Multi-Class Composite N-grams. In experiments, the Multi-Class Composite N-grams result in 9.5% lower perplexity and a 16% lower word error rate in speech recognition with a 40% smaller parameter size than conventional word 3-grams.