The i-vector extraction process is affected by several factors such as the noise level, the acoustic content of the observed features, the channel mismatch between the training conditions and the test data, and the duration of the analyzed speech segment. These factors influence both the i–vector estimate and its uncertainty, represented by the i–vector posterior covariance. This paper presents a new PLDA model that, unlike the standard one, exploits the intrinsic i–vector uncertainty. Since the recognition accuracy is known to decrease for short speech segments, and their length is one of the main factors affecting the i–vector covariance, we designed a set of experiments aiming at comparing the standard and the new PLDA models on short speech cuts of variable duration, randomly extracted from the conversations included in the NIST SRE 2010 extended dataset, both from interviews and telephone conversations. Our results on NIST SRE 2010 evaluation data show that in different conditions the new model outperforms the standard PLDA by more than 10% relative when tested on short segments with duration mismatches, and is able to keep the accuracy of the standard model for long enough speaker segments. This technique has also been successfully tested in the NIST SRE 2012 evaluation.

On the use of i-vector posterior distributions in Probabilistic Linear Discriminant Analysis / Cumani, Sandro; Plchot, O.; Laface, Pietro. - In: IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING. - ISSN 2329-9290. - STAMPA. - 22:4(2014), pp. 846-857. [10.1109/TASLP.2014.2308473]

On the use of i-vector posterior distributions in Probabilistic Linear Discriminant Analysis

CUMANI, SANDRO;LAFACE, Pietro
2014

Abstract

The i-vector extraction process is affected by several factors such as the noise level, the acoustic content of the observed features, the channel mismatch between the training conditions and the test data, and the duration of the analyzed speech segment. These factors influence both the i–vector estimate and its uncertainty, represented by the i–vector posterior covariance. This paper presents a new PLDA model that, unlike the standard one, exploits the intrinsic i–vector uncertainty. Since the recognition accuracy is known to decrease for short speech segments, and their length is one of the main factors affecting the i–vector covariance, we designed a set of experiments aiming at comparing the standard and the new PLDA models on short speech cuts of variable duration, randomly extracted from the conversations included in the NIST SRE 2010 extended dataset, both from interviews and telephone conversations. Our results on NIST SRE 2010 evaluation data show that in different conditions the new model outperforms the standard PLDA by more than 10% relative when tested on short segments with duration mismatches, and is able to keep the accuracy of the standard model for long enough speaker segments. This technique has also been successfully tested in the NIST SRE 2012 evaluation.
File in questo prodotto:
File Dimensione Formato  
On the use of i–vector posterior distributions in Probabilistic Linear Discriminant Analysis.pdf

accesso aperto

Descrizione: Articolo principale
Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 241.92 kB
Formato Adobe PDF
241.92 kB Adobe PDF Visualizza/Apri
06748853.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 2.59 MB
Formato Adobe PDF
2.59 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
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/11583/2532092