Most of the state–of–the–art speaker recognition systems use a compact representation of spoken utterances referred to as i–vectors. 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 storage needs for i–vector extraction, but is also fast. 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 any other known method.

Fast and Memory Effective I-Vector Extraction Using a Factorized Sub-Space / Cumani, Sandro; Laface, Pietro. - STAMPA. - 1:(2013), pp. 1599-1603. ((Intervento presentato al convegno Interspeech 2013 tenutosi a Lyon (France) nel 25-29 Aug.

Fast and Memory Effective I-Vector Extraction Using a Factorized Sub-Space

CUMANI, SANDRO;LAFACE, Pietro
2013

Abstract

Most of the state–of–the–art speaker recognition systems use a compact representation of spoken utterances referred to as i–vectors. 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 storage needs for i–vector extraction, but is also fast. 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 any other known method.
File in questo prodotto:
File Dimensione Formato  
2513864.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 86.71 kB
Formato Adobe PDF
86.71 kB Adobe PDF Visualizza/Apri
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/11583/2513864
 Attenzione

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