Dataset-invariant covariance normalization for out-domain PLDA speaker verification
Data(s) |
01/05/2015
|
---|---|
Resumo |
In this paper we introduce a novel domain-invariant covariance normalization (DICN) technique to relocate both in-domain and out-domain i-vectors into a third dataset-invariant space, providing an improvement for out-domain PLDA speaker verification with a very small number of unlabelled in-domain adaptation i-vectors. By capturing the dataset variance from a global mean using both development out-domain i-vectors and limited unlabelled in-domain i-vectors, we could obtain domain- invariant representations of PLDA training data. The DICN- compensated out-domain PLDA system is shown to perform as well as in-domain PLDA training with as few as 500 unlabelled in-domain i-vectors for NIST-2010 SRE and 2000 unlabelled in-domain i-vectors for NIST-2008 SRE, and considerable relative improvement over both out-domain and in-domain PLDA development if more are available. |
Formato |
application/pdf |
Identificador | |
Publicador |
International Speech Communication Association |
Relação |
http://eprints.qut.edu.au/85083/1/491.pdf http://www.isca-speech.org/archive/interspeech_2015/i15_1017.html Rahman, Md Hafizur, Kanagasundaram, Ahilan, Dean, David, & Sridharan, Sridha (2015) Dataset-invariant covariance normalization for out-domain PLDA speaker verification. In Proceedings of the 16th Annual Conference of the International Speech Communication Association, Interspeech 2015, International Speech Communication Association, Maritim International Congress Center, Dresden, Germany, pp. 1017-1021. http://purl.org/au-research/grants/ARC/LP130100110 |
Direitos |
Copyright 2015 [Please consult the author] |
Fonte |
School of Electrical Engineering & Computer Science; Science & Engineering Faculty |
Palavras-Chave | #speaker verification #PLDA #DICN #domain adaptation |
Tipo |
Conference Paper |