Pronunciation variants description using recognition error modeling with phonetic derivation hypotheses

Hideharu Nakajima, Yoshinori Sagisaka, Hirofumi Yamamoto

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper proposes a new method of pronunciation variant generation for reducing word error rate in conversational speech recognition. In particular, this paper focuses on the generation of alternative pronunciations from canonical forms by using the phonological knowledge derived from the analysis of a phonetic transcription corpus. The experimental results show that the pronunciation variation generated by the proposed method provides slightly better performance than a method based on manually written pronunciation. These results also demonstrate the applicability of phonological knowledge-based generation of pronunciation variation.

Original languageEnglish
Title of host publication6th International Conference on Spoken Language Processing, ICSLP 2000
PublisherInternational Speech Communication Association
ISBN (Electronic)7801501144, 9787801501141
Publication statusPublished - 2000
Externally publishedYes
Event6th International Conference on Spoken Language Processing, ICSLP 2000 - Beijing, China
Duration: 2000 Oct 162000 Oct 20

Other

Other6th International Conference on Spoken Language Processing, ICSLP 2000
CountryChina
CityBeijing
Period00/10/1600/10/20

Fingerprint

phonetics
knowledge
performance
Modeling

Keywords

  • Corpus based approach
  • Multiple pronunciation generation
  • Phonological knowledge
  • Speech variants

ASJC Scopus subject areas

  • Linguistics and Language
  • Language and Linguistics

Cite this

Nakajima, H., Sagisaka, Y., & Yamamoto, H. (2000). Pronunciation variants description using recognition error modeling with phonetic derivation hypotheses. In 6th International Conference on Spoken Language Processing, ICSLP 2000 International Speech Communication Association.

Pronunciation variants description using recognition error modeling with phonetic derivation hypotheses. / Nakajima, Hideharu; Sagisaka, Yoshinori; Yamamoto, Hirofumi.

6th International Conference on Spoken Language Processing, ICSLP 2000. International Speech Communication Association, 2000.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nakajima, H, Sagisaka, Y & Yamamoto, H 2000, Pronunciation variants description using recognition error modeling with phonetic derivation hypotheses. in 6th International Conference on Spoken Language Processing, ICSLP 2000. International Speech Communication Association, 6th International Conference on Spoken Language Processing, ICSLP 2000, Beijing, China, 00/10/16.
Nakajima H, Sagisaka Y, Yamamoto H. Pronunciation variants description using recognition error modeling with phonetic derivation hypotheses. In 6th International Conference on Spoken Language Processing, ICSLP 2000. International Speech Communication Association. 2000
Nakajima, Hideharu ; Sagisaka, Yoshinori ; Yamamoto, Hirofumi. / Pronunciation variants description using recognition error modeling with phonetic derivation hypotheses. 6th International Conference on Spoken Language Processing, ICSLP 2000. International Speech Communication Association, 2000.
@inproceedings{764cbf57f045460598cc5e8b319bbf3b,
title = "Pronunciation variants description using recognition error modeling with phonetic derivation hypotheses",
abstract = "This paper proposes a new method of pronunciation variant generation for reducing word error rate in conversational speech recognition. In particular, this paper focuses on the generation of alternative pronunciations from canonical forms by using the phonological knowledge derived from the analysis of a phonetic transcription corpus. The experimental results show that the pronunciation variation generated by the proposed method provides slightly better performance than a method based on manually written pronunciation. These results also demonstrate the applicability of phonological knowledge-based generation of pronunciation variation.",
keywords = "Corpus based approach, Multiple pronunciation generation, Phonological knowledge, Speech variants",
author = "Hideharu Nakajima and Yoshinori Sagisaka and Hirofumi Yamamoto",
year = "2000",
language = "English",
booktitle = "6th International Conference on Spoken Language Processing, ICSLP 2000",
publisher = "International Speech Communication Association",

}

TY - GEN

T1 - Pronunciation variants description using recognition error modeling with phonetic derivation hypotheses

AU - Nakajima, Hideharu

AU - Sagisaka, Yoshinori

AU - Yamamoto, Hirofumi

PY - 2000

Y1 - 2000

N2 - This paper proposes a new method of pronunciation variant generation for reducing word error rate in conversational speech recognition. In particular, this paper focuses on the generation of alternative pronunciations from canonical forms by using the phonological knowledge derived from the analysis of a phonetic transcription corpus. The experimental results show that the pronunciation variation generated by the proposed method provides slightly better performance than a method based on manually written pronunciation. These results also demonstrate the applicability of phonological knowledge-based generation of pronunciation variation.

AB - This paper proposes a new method of pronunciation variant generation for reducing word error rate in conversational speech recognition. In particular, this paper focuses on the generation of alternative pronunciations from canonical forms by using the phonological knowledge derived from the analysis of a phonetic transcription corpus. The experimental results show that the pronunciation variation generated by the proposed method provides slightly better performance than a method based on manually written pronunciation. These results also demonstrate the applicability of phonological knowledge-based generation of pronunciation variation.

KW - Corpus based approach

KW - Multiple pronunciation generation

KW - Phonological knowledge

KW - Speech variants

UR - http://www.scopus.com/inward/record.url?scp=84871615734&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84871615734&partnerID=8YFLogxK

M3 - Conference contribution

BT - 6th International Conference on Spoken Language Processing, ICSLP 2000

PB - International Speech Communication Association

ER -