Analysis of acoustic models trained on a large-scale Japanese speech database

Tomoko Matsui; Masaki Naito; Yoshinori Sagisaka; Kozo Okuda; Satoshi Nakamura

Analysis of acoustic models trained on a large-scale Japanese speech database

Tomoko Matsui, Masaki Naito, Yoshinori Sagisaka, Kozo Okuda, Satoshi Nakamura

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper investigates the performance of speaker-independent (SI) acoustic hidden-Markov-models (HMMs) trained with a huge Japanese speech database, and discusses the efficiency and task-independency involved. The database consists of read and spontaneous speech uttered by 3,771 speakers. The speech involves wide distributions with respect to region and age to capture the Japanese speech characteristics as best as possible. Recognition experiments using the spontaneous speech show that task-independent acoustic models can be created when training data with a huge number of speakers is available.

Original language	English
Title of host publication	6th International Conference on Spoken Language Processing, ICSLP 2000
Publisher	International Speech Communication Association
ISBN (Electronic)	7801501144, 9787801501141
Publication status	Published - 2000
Externally published	Yes
Event	6th International Conference on Spoken Language Processing, ICSLP 2000 - Beijing, China Duration: 2000 Oct 16 → 2000 Oct 20

Other

Other	6th International Conference on Spoken Language Processing, ICSLP 2000
Country/Territory	China
City	Beijing
Period	00/10/16 → 00/10/20

ASJC Scopus subject areas

Linguistics and Language
Language and Linguistics

Cite this

@inproceedings{614aa3a6ed934bf8ae11b750e4aa6efe,

title = "Analysis of acoustic models trained on a large-scale Japanese speech database",

abstract = "This paper investigates the performance of speaker-independent (SI) acoustic hidden-Markov-models (HMMs) trained with a huge Japanese speech database, and discusses the efficiency and task-independency involved. The database consists of read and spontaneous speech uttered by 3,771 speakers. The speech involves wide distributions with respect to region and age to capture the Japanese speech characteristics as best as possible. Recognition experiments using the spontaneous speech show that task-independent acoustic models can be created when training data with a huge number of speakers is available.",

author = "Tomoko Matsui and Masaki Naito and Yoshinori Sagisaka and Kozo Okuda and Satoshi Nakamura",

year = "2000",

language = "English",

booktitle = "6th International Conference on Spoken Language Processing, ICSLP 2000",

publisher = "International Speech Communication Association",

note = "6th International Conference on Spoken Language Processing, ICSLP 2000 ; Conference date: 16-10-2000 Through 20-10-2000",

}

TY - GEN

T1 - Analysis of acoustic models trained on a large-scale Japanese speech database

AU - Matsui, Tomoko

AU - Naito, Masaki

AU - Sagisaka, Yoshinori

AU - Okuda, Kozo

AU - Nakamura, Satoshi

PY - 2000

Y1 - 2000

N2 - This paper investigates the performance of speaker-independent (SI) acoustic hidden-Markov-models (HMMs) trained with a huge Japanese speech database, and discusses the efficiency and task-independency involved. The database consists of read and spontaneous speech uttered by 3,771 speakers. The speech involves wide distributions with respect to region and age to capture the Japanese speech characteristics as best as possible. Recognition experiments using the spontaneous speech show that task-independent acoustic models can be created when training data with a huge number of speakers is available.

AB - This paper investigates the performance of speaker-independent (SI) acoustic hidden-Markov-models (HMMs) trained with a huge Japanese speech database, and discusses the efficiency and task-independency involved. The database consists of read and spontaneous speech uttered by 3,771 speakers. The speech involves wide distributions with respect to region and age to capture the Japanese speech characteristics as best as possible. Recognition experiments using the spontaneous speech show that task-independent acoustic models can be created when training data with a huge number of speakers is available.

UR - http://www.scopus.com/inward/record.url?scp=85009080621&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009080621&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85009080621

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

PB - International Speech Communication Association

T2 - 6th International Conference on Spoken Language Processing, ICSLP 2000

Y2 - 16 October 2000 through 20 October 2000

ER -

Analysis of acoustic models trained on a large-scale Japanese speech database

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this