This paper proposes a density model transformation for speaker recognition systems based on i–vectors and Probabilistic Linear Discriminant Analysis (PLDA) classification. The PLDA model assumes that the i-vectors are distributed according to the standard normal distribution, whereas it is well known that this is not the case. Experiments have shown that the i–vector are better modeled, for example, by a Heavy–Tailed distribution, and that significant improvement of the classification performance can be obtained by whitening and length normalizing the i-vectors. In this work we propose to transform the i–vectors, extracted ignoring the classifier that will be used, so that their distribution becomes more suitable to discriminate speakers using PLDA. This is performed by means of a sequence of affine and non–linear transformations whose parameters are obtained by Maximum Likelihood (ML) estimation on the training set. The second contribution of this work is the reduction of the mismatch between the development and test i–vector distributions by means of a scaling factor tuned for the estimated i-vector distribution, rather than by means of a blind length normalization. Our tests performed on the NIST SRE-2010 and SRE-2012 evaluation sets show that improvement of their Cost Functions of the order of 10% can be obtained for both evaluation data.
I–vector transformation and scaling for PLDA based speaker recognition / Cumani, Sandro; Laface, Pietro. - STAMPA. - (2016), pp. 39-46. (Intervento presentato al convegno Odyssey 2016 - The Speaker and Language Recognition Workshop tenutosi a Bilbao (Spain) nel 21-24 Giugno 2016).
I–vector transformation and scaling for PLDA based speaker recognition
CUMANI, SANDRO;LAFACE, Pietro
2016
Abstract
This paper proposes a density model transformation for speaker recognition systems based on i–vectors and Probabilistic Linear Discriminant Analysis (PLDA) classification. The PLDA model assumes that the i-vectors are distributed according to the standard normal distribution, whereas it is well known that this is not the case. Experiments have shown that the i–vector are better modeled, for example, by a Heavy–Tailed distribution, and that significant improvement of the classification performance can be obtained by whitening and length normalizing the i-vectors. In this work we propose to transform the i–vectors, extracted ignoring the classifier that will be used, so that their distribution becomes more suitable to discriminate speakers using PLDA. This is performed by means of a sequence of affine and non–linear transformations whose parameters are obtained by Maximum Likelihood (ML) estimation on the training set. The second contribution of this work is the reduction of the mismatch between the development and test i–vector distributions by means of a scaling factor tuned for the estimated i-vector distribution, rather than by means of a blind length normalization. Our tests performed on the NIST SRE-2010 and SRE-2012 evaluation sets show that improvement of their Cost Functions of the order of 10% can be obtained for both evaluation data.Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2645216
Attenzione
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo