This paper describes the Nuance–Politecnico di Torino (NPT) speaker recognition system submitted to the NIST SRE12 evaluation campaign. Included are the results of postevaluation tests, focusing on the analysis of the effects of score normalization and condition-dependent calibration. The submitted system combines the results of five acoustic recognizers all based on Gaussian Mixture Models (GMMs). Each system has its own front end, with features differing by their type and dimension. We illustrate the process of development data selection and configuration of state-of-the-art technology, which contributed to obtaining good performance in all the test conditions proposed in this evaluation.
Nuance - Politecnico di Torino’s 2012 NIST Speaker Recognition Evaluation System / Colibro, D.; Vairc, ; Farrell, K.; Krause, N.; Karvitsky, G.; Cumani, Sandro; Laface, Pietro. - STAMPA. - 1:(2013), pp. 1996-2000. (Intervento presentato al convegno 14th Annual Conference of the International Speech Communication Association (Interspeech 2013). tenutosi a Lyon (France) nel 25-29 Aug 2013).
Nuance - Politecnico di Torino’s 2012 NIST Speaker Recognition Evaluation System
CUMANI, SANDRO;LAFACE, Pietro
2013
Abstract
This paper describes the Nuance–Politecnico di Torino (NPT) speaker recognition system submitted to the NIST SRE12 evaluation campaign. Included are the results of postevaluation tests, focusing on the analysis of the effects of score normalization and condition-dependent calibration. The submitted system combines the results of five acoustic recognizers all based on Gaussian Mixture Models (GMMs). Each system has its own front end, with features differing by their type and dimension. We illustrate the process of development data selection and configuration of state-of-the-art technology, which contributed to obtaining good performance in all the test conditions proposed in this evaluation.File | Dimensione | Formato | |
---|---|---|---|
Nuance - Politecnico di Torino's 2513867.pdf
accesso aperto
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
Pubblico - Tutti i diritti riservati
Dimensione
315.59 kB
Formato
Adobe PDF
|
315.59 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2513867
Attenzione
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo