Text-independent MFCCs vectors classification improvement using local ICA

Abdenebi Rouigueb; Salim Chitroub; Ahmed Bouridane

doi:10.1109/MLSP.2013.6661941

Text-independent MFCCs vectors classification improvement using local ICA

Abdenebi Rouigueb, Salim Chitroub, Ahmed Bouridane

Research output: Contribution to journal › Article › peer-review

Abstract

In this paper, we propose a new classification scheme of MFCCs vectors in the context of speaker identification. The solution is built around the binary SVM classification between each speaker class and the background model class over the underlying spaces of the local independent components analysis using clustering. Experiments have been conducted on a sample of the MOBIO corpus.

Original language	English
Pages (from-to)	1-6
Journal	IEEE International Workshop on Machine Learning for Signal Processing, MLSP
DOIs	https://doi.org/10.1109/MLSP.2013.6661941
Publication status	Published - 2013
Event	2013 IEEE International Workshop on Machine Learning for Signal Processing (MLSP) - Southampton Duration: 1 Jan 2013 → …

Keywords

background model
local independent component analysis
speaker recognition
text-independent

Access to Document

10.1109/MLSP.2013.6661941

Cite this

@article{8299dd38717e4b4bb1a516105a9ceeb5,

title = "Text-independent MFCCs vectors classification improvement using local ICA",

abstract = "In this paper, we propose a new classification scheme of MFCCs vectors in the context of speaker identification. The solution is built around the binary SVM classification between each speaker class and the background model class over the underlying spaces of the local independent components analysis using clustering. Experiments have been conducted on a sample of the MOBIO corpus.",

keywords = "background model, local independent component analysis, speaker recognition, text-independent",

author = "Abdenebi Rouigueb and Salim Chitroub and Ahmed Bouridane",

year = "2013",

doi = "10.1109/MLSP.2013.6661941",

language = "English",

pages = "1--6",

journal = "IEEE International Workshop on Machine Learning for Signal Processing, MLSP",

issn = "2378-928X",

publisher = "IEEE",

note = "2013 IEEE International Workshop on Machine Learning for Signal Processing (MLSP) ; Conference date: 01-01-2013",

}

TY - JOUR

T1 - Text-independent MFCCs vectors classification improvement using local ICA

AU - Rouigueb, Abdenebi

AU - Chitroub, Salim

AU - Bouridane, Ahmed

PY - 2013

Y1 - 2013

N2 - In this paper, we propose a new classification scheme of MFCCs vectors in the context of speaker identification. The solution is built around the binary SVM classification between each speaker class and the background model class over the underlying spaces of the local independent components analysis using clustering. Experiments have been conducted on a sample of the MOBIO corpus.

AB - In this paper, we propose a new classification scheme of MFCCs vectors in the context of speaker identification. The solution is built around the binary SVM classification between each speaker class and the background model class over the underlying spaces of the local independent components analysis using clustering. Experiments have been conducted on a sample of the MOBIO corpus.

KW - background model

KW - local independent component analysis

KW - speaker recognition

KW - text-independent

U2 - 10.1109/MLSP.2013.6661941

DO - 10.1109/MLSP.2013.6661941

M3 - Article

SN - 2378-928X

SP - 1

EP - 6

JO - IEEE International Workshop on Machine Learning for Signal Processing, MLSP

JF - IEEE International Workshop on Machine Learning for Signal Processing, MLSP

T2 - 2013 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)

Y2 - 1 January 2013

ER -

Text-independent MFCCs vectors classification improvement using local ICA

Abstract

Keywords

Access to Document

Fingerprint

Cite this