Pronunciation variant analysis using speaking style parallel corpus

Hideharu Nakajima, Izumi Hiranoy, Yoshinori Sagisaka, Katsuhiko Shiraiy

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

Abstract

To improve the recognition accuracy for spontaneous conversational speech, we collected a corpus to study how spontaneous conversational speech differs from read style speech. The corpus consists of two parts: 1) spontaneous conversational speech and 2) read speech with the same word transcriptions as the conversational speech. In word and phone recognition experiments, it was confirmed that, for the Japanese language, the recognition of spontaneous speech is harder than that of read speech. By comparing of recognition results, we found that, both in the occurrence of errors appearing with speaking style changes, and in the types of pronunciation variants, there are differences that depend on the linguistic categories that misrecognized words belong to. We confirmed that linguistic categories also affect pronunciation variants that deteriorate the recognition accuracy.

Original languageEnglish
Title of host publicationEUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology
PublisherInternational Speech Communication Association
Pages65-68
Number of pages4
ISBN (Electronic)8790834100, 9788790834104
Publication statusPublished - 2001
Externally publishedYes
Event7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001 - Aalborg, Denmark
Duration: 2001 Sep 32001 Sep 7

Other

Other7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001
CountryDenmark
CityAalborg
Period01/9/301/9/7

Fingerprint

speaking
Linguistics
linguistics
Transcription
experiment
language
Experiments

ASJC Scopus subject areas

  • Communication
  • Linguistics and Language
  • Computer Science Applications
  • Software

Cite this

Nakajima, H., Hiranoy, I., Sagisaka, Y., & Shiraiy, K. (2001). Pronunciation variant analysis using speaking style parallel corpus. In EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology (pp. 65-68). International Speech Communication Association.

Pronunciation variant analysis using speaking style parallel corpus. / Nakajima, Hideharu; Hiranoy, Izumi; Sagisaka, Yoshinori; Shiraiy, Katsuhiko.

EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology. International Speech Communication Association, 2001. p. 65-68.

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

Nakajima, H, Hiranoy, I, Sagisaka, Y & Shiraiy, K 2001, Pronunciation variant analysis using speaking style parallel corpus. in EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology. International Speech Communication Association, pp. 65-68, 7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001, Aalborg, Denmark, 01/9/3.
Nakajima H, Hiranoy I, Sagisaka Y, Shiraiy K. Pronunciation variant analysis using speaking style parallel corpus. In EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology. International Speech Communication Association. 2001. p. 65-68
Nakajima, Hideharu ; Hiranoy, Izumi ; Sagisaka, Yoshinori ; Shiraiy, Katsuhiko. / Pronunciation variant analysis using speaking style parallel corpus. EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology. International Speech Communication Association, 2001. pp. 65-68
@inproceedings{adee32126d574ba4be802dbaf891c65a,
title = "Pronunciation variant analysis using speaking style parallel corpus",
abstract = "To improve the recognition accuracy for spontaneous conversational speech, we collected a corpus to study how spontaneous conversational speech differs from read style speech. The corpus consists of two parts: 1) spontaneous conversational speech and 2) read speech with the same word transcriptions as the conversational speech. In word and phone recognition experiments, it was confirmed that, for the Japanese language, the recognition of spontaneous speech is harder than that of read speech. By comparing of recognition results, we found that, both in the occurrence of errors appearing with speaking style changes, and in the types of pronunciation variants, there are differences that depend on the linguistic categories that misrecognized words belong to. We confirmed that linguistic categories also affect pronunciation variants that deteriorate the recognition accuracy.",
author = "Hideharu Nakajima and Izumi Hiranoy and Yoshinori Sagisaka and Katsuhiko Shiraiy",
year = "2001",
language = "English",
pages = "65--68",
booktitle = "EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology",
publisher = "International Speech Communication Association",

}

TY - GEN

T1 - Pronunciation variant analysis using speaking style parallel corpus

AU - Nakajima, Hideharu

AU - Hiranoy, Izumi

AU - Sagisaka, Yoshinori

AU - Shiraiy, Katsuhiko

PY - 2001

Y1 - 2001

N2 - To improve the recognition accuracy for spontaneous conversational speech, we collected a corpus to study how spontaneous conversational speech differs from read style speech. The corpus consists of two parts: 1) spontaneous conversational speech and 2) read speech with the same word transcriptions as the conversational speech. In word and phone recognition experiments, it was confirmed that, for the Japanese language, the recognition of spontaneous speech is harder than that of read speech. By comparing of recognition results, we found that, both in the occurrence of errors appearing with speaking style changes, and in the types of pronunciation variants, there are differences that depend on the linguistic categories that misrecognized words belong to. We confirmed that linguistic categories also affect pronunciation variants that deteriorate the recognition accuracy.

AB - To improve the recognition accuracy for spontaneous conversational speech, we collected a corpus to study how spontaneous conversational speech differs from read style speech. The corpus consists of two parts: 1) spontaneous conversational speech and 2) read speech with the same word transcriptions as the conversational speech. In word and phone recognition experiments, it was confirmed that, for the Japanese language, the recognition of spontaneous speech is harder than that of read speech. By comparing of recognition results, we found that, both in the occurrence of errors appearing with speaking style changes, and in the types of pronunciation variants, there are differences that depend on the linguistic categories that misrecognized words belong to. We confirmed that linguistic categories also affect pronunciation variants that deteriorate the recognition accuracy.

UR - http://www.scopus.com/inward/record.url?scp=85009152058&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009152058&partnerID=8YFLogxK

M3 - Conference contribution

SP - 65

EP - 68

BT - EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology

PB - International Speech Communication Association

ER -