Most of the state–of–the–art speaker recognition systems use a compact representation of spoken utterances referred to as i–vector. Since the “standard” i–vector extraction procedure requires large memory structures and is relatively slow, new approaches have recently been proposed that are able to obtain either accurate solutions at the expense of an increase of the computational load, or fast approximate solutions, which are traded for lower memory costs. We propose a new approach particularly useful for applications that need to minimize their memory requirements. Our solution not only dramatically reduces the memory needs for i–vector extraction, but is also fast and accurate compared to recently proposed approaches. Tested on the female part of the tel-tel extended NIST 2010 evaluation trials, our approach substantially improves the performance with respect to the fastest but inaccurate eigen-decomposition approach, using much less memory than other methods.

Factorized Sub-Space Estimation for Fast and Memory Effective I-vector Extraction / Cumani, Sandro; Laface, Pietro. - In: IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING. - ISSN 2329-9290. - STAMPA. - 22:1(2014), pp. 248-259. [10.1109/TASLP.2013.2290505]

Factorized Sub-Space Estimation for Fast and Memory Effective I-vector Extraction

CUMANI, SANDRO;LAFACE, Pietro
2014

Abstract

Most of the state–of–the–art speaker recognition systems use a compact representation of spoken utterances referred to as i–vector. Since the “standard” i–vector extraction procedure requires large memory structures and is relatively slow, new approaches have recently been proposed that are able to obtain either accurate solutions at the expense of an increase of the computational load, or fast approximate solutions, which are traded for lower memory costs. We propose a new approach particularly useful for applications that need to minimize their memory requirements. Our solution not only dramatically reduces the memory needs for i–vector extraction, but is also fast and accurate compared to recently proposed approaches. Tested on the female part of the tel-tel extended NIST 2010 evaluation trials, our approach substantially improves the performance with respect to the fastest but inaccurate eigen-decomposition approach, using much less memory than other methods.
File in questo prodotto:
File Dimensione Formato  
manuscript-open.pdf

accesso aperto

Tipologia: 1. Preprint / submitted version [pre- review]
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 302.78 kB
Formato Adobe PDF
302.78 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: https://hdl.handle.net/11583/2520689
 Attenzione

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