Timbre Recognition with Combined Stationary and Temporal Features

Shlomo Dubnov; Xavier Rodet

Timbre Recognition with Combined Stationary and Temporal Features

Shlomo Dubnov, Xavier Rodet

Research output: Contribution to journal › Conference article › peer-review

8 Scopus citations

Abstract

In this paper we consider the problem of modeling spectro-temporal behaviour of musical sounds, with applications for musical instrument recognition. Using instanteneous sound features, such as cepstral envelopes and cepstral derivatives, the temporal evolution of the sound is transcribed into a new representation as a sequence of spectral features. Applying information-theoretic sequence matching methods, the sound dynamics can be modeled and compared. Testing this method on recordings of several solo musical pieces of different instrument, excellent matching results were obtained.

Original language	English
Journal	International Computer Music Conference, ICMC Proceedings
State	Published - 1 Jan 1998
Externally published	Yes
Event	24th International Computer Music Conference, ICMC 1998 - Ann Arbor, United States Duration: 1 Oct 1998 → 6 Oct 1998

ASJC Scopus subject areas

Music
Computer Science Applications
Media Technology

Cite this

@article{cdccb93313084310bd2566b78fd3d29f,

title = "Timbre Recognition with Combined Stationary and Temporal Features",

abstract = "In this paper we consider the problem of modeling spectro-temporal behaviour of musical sounds, with applications for musical instrument recognition. Using instanteneous sound features, such as cepstral envelopes and cepstral derivatives, the temporal evolution of the sound is transcribed into a new representation as a sequence of spectral features. Applying information-theoretic sequence matching methods, the sound dynamics can be modeled and compared. Testing this method on recordings of several solo musical pieces of different instrument, excellent matching results were obtained.",

author = "Shlomo Dubnov and Xavier Rodet",

year = "1998",

month = jan,

day = "1",

language = "English",

journal = "International Computer Music Conference, ICMC Proceedings",

issn = "2223-3881",

publisher = "International Computer Music Association",

}

TY - JOUR

T1 - Timbre Recognition with Combined Stationary and Temporal Features

AU - Dubnov, Shlomo

AU - Rodet, Xavier

PY - 1998/1/1

Y1 - 1998/1/1

N2 - In this paper we consider the problem of modeling spectro-temporal behaviour of musical sounds, with applications for musical instrument recognition. Using instanteneous sound features, such as cepstral envelopes and cepstral derivatives, the temporal evolution of the sound is transcribed into a new representation as a sequence of spectral features. Applying information-theoretic sequence matching methods, the sound dynamics can be modeled and compared. Testing this method on recordings of several solo musical pieces of different instrument, excellent matching results were obtained.

AB - In this paper we consider the problem of modeling spectro-temporal behaviour of musical sounds, with applications for musical instrument recognition. Using instanteneous sound features, such as cepstral envelopes and cepstral derivatives, the temporal evolution of the sound is transcribed into a new representation as a sequence of spectral features. Applying information-theoretic sequence matching methods, the sound dynamics can be modeled and compared. Testing this method on recordings of several solo musical pieces of different instrument, excellent matching results were obtained.

UR - http://www.scopus.com/inward/record.url?scp=0037503637&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0037503637

SN - 2223-3881

JO - International Computer Music Conference, ICMC Proceedings

JF - International Computer Music Conference, ICMC Proceedings

T2 - 24th International Computer Music Conference, ICMC 1998

Y2 - 1 October 1998 through 6 October 1998

ER -

Timbre Recognition with Combined Stationary and Temporal Features

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this