Presentation | 1995/11/16 Variable-Order Statistical Language Modeling for Continuous Speech Recognition Hirokazu Masataki, Shoichi Matsunaga, Yoshinori Sagisaka, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this paper, we propose a variable-order N-gram that describe training corpus efficiently by limited number of parameters. Starting from POS bigrams, the proposed scheme creates variable-order N-grams by splitting a POS into finer groups and by adding frequent consecutive word sequences as word-classes. This word-class splitting and consecutive word grouping are carried out incrementally by minimizing the total entropy. Experiments showed that the perplexity of the proposed model for the test corpus is lower than conventional trigram and that this model requires quite smaller number of statistical parameters. By applying this model to speech recognition, we get a better recognition rate than conventionalfixed N-grams. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Continuous Speech Recognition / Statistical Language Modeling / N-gram / perplexity |
Paper # | SP95-73 |
Date of Issue |
Conference Information | |
Committee | SP |
---|---|
Conference Date | 1995/11/16(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Speech (SP) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Variable-Order Statistical Language Modeling for Continuous Speech Recognition |
Sub Title (in English) | |
Keyword(1) | Continuous Speech Recognition |
Keyword(2) | Statistical Language Modeling |
Keyword(3) | N-gram |
Keyword(4) | perplexity |
1st Author's Name | Hirokazu Masataki |
1st Author's Affiliation | ATR Interpreting Telecommunications Research Laboratories() |
2nd Author's Name | Shoichi Matsunaga |
2nd Author's Affiliation | ATR Interpreting Telecommunications Research Laboratories |
3rd Author's Name | Yoshinori Sagisaka |
3rd Author's Affiliation | ATR Interpreting Telecommunications Research Laboratories |
Date | 1995/11/16 |
Paper # | SP95-73 |
Volume (vol) | vol.95 |
Number (no) | 355 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |