Repeat recognition for environmental sounds

Yuya Hattori; Kazushi Ishihara; Kazunori Komatani; Tetsuya Ogata; Hiroshi G. Okuno

Repeat recognition for environmental sounds

Yuya Hattori^*, Kazushi Ishihara, Kazunori Komatani, Tetsuya Ogata, Hiroshi G. Okuno

^*この研究の対応する著者

研究成果: Paper › 査読

1 被引用数 (Scopus)

抄録

This paper focuses on recognition of repeats in continuous environmental sounds. Environmental sounds, that are very informative in our daily lives, often repeat several times. Repeat recognition for environmental sounds is essential for compact representation of those sounds and for forecasting the future. In our method, input environmental sound signal is partitioned into several units according to the shapes of the power envelopes, and the auditory distance between every pair of units is computed. Repeating parts are then detected by using the approximate matching algorithm. Experimental results showed the 73.3% of recognition rate in counting the repeats of 30 environmental sounds, the length of each of which ranged from 20 seconds to 2 minutes.

本文言語	English
ページ	83-88
ページ数	6
出版ステータス	Published - 2004 12月 1
外部発表	はい
イベント	RO-MAN 2004 - 13th IEEE International Workshop on Robot and Human Interactive Communication - Okayama, Japan 継続期間: 2004 9月 20 → 2004 9月 22

Conference

Conference	RO-MAN 2004 - 13th IEEE International Workshop on Robot and Human Interactive Communication
国/地域	Japan
City	Okayama
Period	04/9/20 → 04/9/22

ASJC Scopus subject areas

工学（全般）

他のファイルとリンク

引用スタイル

@conference{d38b43fb8db74331a439572a20b0bc4e,

title = "Repeat recognition for environmental sounds",

abstract = "This paper focuses on recognition of repeats in continuous environmental sounds. Environmental sounds, that are very informative in our daily lives, often repeat several times. Repeat recognition for environmental sounds is essential for compact representation of those sounds and for forecasting the future. In our method, input environmental sound signal is partitioned into several units according to the shapes of the power envelopes, and the auditory distance between every pair of units is computed. Repeating parts are then detected by using the approximate matching algorithm. Experimental results showed the 73.3% of recognition rate in counting the repeats of 30 environmental sounds, the length of each of which ranged from 20 seconds to 2 minutes.",

author = "Yuya Hattori and Kazushi Ishihara and Kazunori Komatani and Tetsuya Ogata and Okuno, {Hiroshi G.}",

year = "2004",

month = dec,

day = "1",

language = "English",

pages = "83--88",

note = "RO-MAN 2004 - 13th IEEE International Workshop on Robot and Human Interactive Communication ; Conference date: 20-09-2004 Through 22-09-2004",

}

TY - CONF

T1 - Repeat recognition for environmental sounds

AU - Hattori, Yuya

AU - Ishihara, Kazushi

AU - Komatani, Kazunori

AU - Ogata, Tetsuya

AU - Okuno, Hiroshi G.

PY - 2004/12/1

Y1 - 2004/12/1

N2 - This paper focuses on recognition of repeats in continuous environmental sounds. Environmental sounds, that are very informative in our daily lives, often repeat several times. Repeat recognition for environmental sounds is essential for compact representation of those sounds and for forecasting the future. In our method, input environmental sound signal is partitioned into several units according to the shapes of the power envelopes, and the auditory distance between every pair of units is computed. Repeating parts are then detected by using the approximate matching algorithm. Experimental results showed the 73.3% of recognition rate in counting the repeats of 30 environmental sounds, the length of each of which ranged from 20 seconds to 2 minutes.

AB - This paper focuses on recognition of repeats in continuous environmental sounds. Environmental sounds, that are very informative in our daily lives, often repeat several times. Repeat recognition for environmental sounds is essential for compact representation of those sounds and for forecasting the future. In our method, input environmental sound signal is partitioned into several units according to the shapes of the power envelopes, and the auditory distance between every pair of units is computed. Repeating parts are then detected by using the approximate matching algorithm. Experimental results showed the 73.3% of recognition rate in counting the repeats of 30 environmental sounds, the length of each of which ranged from 20 seconds to 2 minutes.

UR - http://www.scopus.com/inward/record.url?scp=20444432676&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=20444432676&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:20444432676

SP - 83

EP - 88

T2 - RO-MAN 2004 - 13th IEEE International Workshop on Robot and Human Interactive Communication

Y2 - 20 September 2004 through 22 September 2004

ER -

Repeat recognition for environmental sounds

抄録

Conference

ASJC Scopus subject areas

他のファイルとリンク

フィンガープリント

引用スタイル