Fast and simple iterative algorithm of Lp-norm minimization for under-determined speech separation

Yasuharu Hirasawa, Naoki Yasuraoka, Toru Takahashi, Tetsuya Ogata, Hiroshi G. Okuno

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

Abstract

This paper presents an efficient algorithm to solve Lp-norm minimization problem for under-determined speech separation; that is, for the case that there are more sound sources than microphones. We employ an auxiliary function method in order to derive update rules under the assumption that the amplitude of each sound source follows generalized Gaussian distribution. Experiments reveal that our method solves the L1-norm minimization problem ten times faster than a general solver, and also solves Lp-norm minimization problem efficiently, especially when the parameter p is small; when p is not more than 0.7, it runs in real-time without loss of separation quality.

Original languageEnglish
Title of host publicationProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Pages1745-1748
Number of pages4
Publication statusPublished - 2011
Externally publishedYes
Event12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011 - Florence, Italy
Duration: 2011 Aug 272011 Aug 31

Other

Other12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011
CountryItaly
CityFlorence
Period11/8/2711/8/31

Fingerprint

Lp-norm
Minimization Problem
Iterative Algorithm
Acoustic waves
Auxiliary Function
L1-norm
Gaussian distribution
Microphones
Efficient Algorithms
Update
Real-time
Experiment
Speech
Experiments
Sound

Keywords

  • Auxiliary function method
  • Lp-norm minimization
  • Speech separation
  • Under-determined condition

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modelling and Simulation

Cite this

Hirasawa, Y., Yasuraoka, N., Takahashi, T., Ogata, T., & Okuno, H. G. (2011). Fast and simple iterative algorithm of Lp-norm minimization for under-determined speech separation. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH (pp. 1745-1748)

Fast and simple iterative algorithm of Lp-norm minimization for under-determined speech separation. / Hirasawa, Yasuharu; Yasuraoka, Naoki; Takahashi, Toru; Ogata, Tetsuya; Okuno, Hiroshi G.

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2011. p. 1745-1748.

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

Hirasawa, Y, Yasuraoka, N, Takahashi, T, Ogata, T & Okuno, HG 2011, Fast and simple iterative algorithm of Lp-norm minimization for under-determined speech separation. in Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. pp. 1745-1748, 12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011, Florence, Italy, 11/8/27.
Hirasawa Y, Yasuraoka N, Takahashi T, Ogata T, Okuno HG. Fast and simple iterative algorithm of Lp-norm minimization for under-determined speech separation. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2011. p. 1745-1748
Hirasawa, Yasuharu ; Yasuraoka, Naoki ; Takahashi, Toru ; Ogata, Tetsuya ; Okuno, Hiroshi G. / Fast and simple iterative algorithm of Lp-norm minimization for under-determined speech separation. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2011. pp. 1745-1748
@inproceedings{51761e13825948c899248c6ec052019c,
title = "Fast and simple iterative algorithm of Lp-norm minimization for under-determined speech separation",
abstract = "This paper presents an efficient algorithm to solve Lp-norm minimization problem for under-determined speech separation; that is, for the case that there are more sound sources than microphones. We employ an auxiliary function method in order to derive update rules under the assumption that the amplitude of each sound source follows generalized Gaussian distribution. Experiments reveal that our method solves the L1-norm minimization problem ten times faster than a general solver, and also solves Lp-norm minimization problem efficiently, especially when the parameter p is small; when p is not more than 0.7, it runs in real-time without loss of separation quality.",
keywords = "Auxiliary function method, Lp-norm minimization, Speech separation, Under-determined condition",
author = "Yasuharu Hirasawa and Naoki Yasuraoka and Toru Takahashi and Tetsuya Ogata and Okuno, {Hiroshi G.}",
year = "2011",
language = "English",
pages = "1745--1748",
booktitle = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",

}

TY - GEN

T1 - Fast and simple iterative algorithm of Lp-norm minimization for under-determined speech separation

AU - Hirasawa, Yasuharu

AU - Yasuraoka, Naoki

AU - Takahashi, Toru

AU - Ogata, Tetsuya

AU - Okuno, Hiroshi G.

PY - 2011

Y1 - 2011

N2 - This paper presents an efficient algorithm to solve Lp-norm minimization problem for under-determined speech separation; that is, for the case that there are more sound sources than microphones. We employ an auxiliary function method in order to derive update rules under the assumption that the amplitude of each sound source follows generalized Gaussian distribution. Experiments reveal that our method solves the L1-norm minimization problem ten times faster than a general solver, and also solves Lp-norm minimization problem efficiently, especially when the parameter p is small; when p is not more than 0.7, it runs in real-time without loss of separation quality.

AB - This paper presents an efficient algorithm to solve Lp-norm minimization problem for under-determined speech separation; that is, for the case that there are more sound sources than microphones. We employ an auxiliary function method in order to derive update rules under the assumption that the amplitude of each sound source follows generalized Gaussian distribution. Experiments reveal that our method solves the L1-norm minimization problem ten times faster than a general solver, and also solves Lp-norm minimization problem efficiently, especially when the parameter p is small; when p is not more than 0.7, it runs in real-time without loss of separation quality.

KW - Auxiliary function method

KW - Lp-norm minimization

KW - Speech separation

KW - Under-determined condition

UR - http://www.scopus.com/inward/record.url?scp=84865796621&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865796621&partnerID=8YFLogxK

M3 - Conference contribution

SP - 1745

EP - 1748

BT - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

ER -