The variability of the channel and environment is one of the most important factors affecting the performance of text-independent speaker verification systems. The best techniques for channel compensation are model based. Most of them have been proposed for Gaussian mixture models, while in the feature domain blind channel compensation is usually performed. The aim of this work is to explore techniques that allow more accurate intersession compensation in the feature domain. Compensating the features rather than the models has the advantage that the transformed parameters can be used with models of a different nature and complexity and for different tasks. In this paper, we evaluate the effects of the compensation of the intersession variability obtained by means of the channel factors approach. In particular, we compare channel variability modeling in the usual Gaussian mixture model domain, and our proposed feature domain compensation technique. We show that the two approaches lead to similar results on the NIST 2005 Speaker Recognition Evaluation data with a reduced computation cost. We also report the results of a system, based on the intersession compensation technique in the feature space that was among the best participants in the NIST 2006 Speaker Recognition Evaluation. Moreover, we show how we obtained significant performance improvement in language recognition by estimating and compensating, in the feature domain, the distortions due to interspeaker variability within the same language. Index Terms—Factor analy

Compensation of Nuisance Factors for Speaker and Language Recognition / Castaldo, Fabio; Colibro, D; Dalmasso, E; Laface, Pietro; Vair, C.. - In: IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING. - ISSN 1558-7916. - STAMPA. - 15-7:(2007), pp. 1969-1978. [10.1109/TASL.2007.901823]

Compensation of Nuisance Factors for Speaker and Language Recognition

CASTALDO, FABIO;LAFACE, Pietro;
2007

Abstract

The variability of the channel and environment is one of the most important factors affecting the performance of text-independent speaker verification systems. The best techniques for channel compensation are model based. Most of them have been proposed for Gaussian mixture models, while in the feature domain blind channel compensation is usually performed. The aim of this work is to explore techniques that allow more accurate intersession compensation in the feature domain. Compensating the features rather than the models has the advantage that the transformed parameters can be used with models of a different nature and complexity and for different tasks. In this paper, we evaluate the effects of the compensation of the intersession variability obtained by means of the channel factors approach. In particular, we compare channel variability modeling in the usual Gaussian mixture model domain, and our proposed feature domain compensation technique. We show that the two approaches lead to similar results on the NIST 2005 Speaker Recognition Evaluation data with a reduced computation cost. We also report the results of a system, based on the intersession compensation technique in the feature space that was among the best participants in the NIST 2006 Speaker Recognition Evaluation. Moreover, we show how we obtained significant performance improvement in language recognition by estimating and compensating, in the feature domain, the distortions due to interspeaker variability within the same language. Index Terms—Factor analy
File in questo prodotto:
File Dimensione Formato  
07-ASLP-Trans-manuscript-v18-open.pdf

accesso aperto

Tipologia: 1. Preprint / submitted version [pre- review]
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 249.28 kB
Formato Adobe PDF
249.28 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11583/1646600
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo