Deep belief networks for i-vector based speaker recognition
Document typeConference report
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Rights accessRestricted access - publisher's policy
The use of Deep Belief Networks (DBNs) is proposed in this paper to model discriminatively target and impostor i-vectors in a speaker verification task. The authors propose to adapt the network parameters of each speaker from a background model, which will be referred to as Universal DBN (UDBN). It is also suggested to backpropagate class errors up to only one layer for few iterations before to train the network. Additionally, an impostor selection method is introduced which helps the DBN to outperform the cosine distance classifier. The evaluation is performed on the core test condition of the NIST SRE 2006 corpora, and it is shown that 10% and 8% relative improvements of EER and minDCF can be achieved, respectively.
CitationGhahabi, O.; Hernando, J. Deep belief networks for i-vector based speaker recognition. A: IEEE International Conference on Acoustics, Speech, and Signal Processing. "2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014): Florence, Italy, 4-9 May 2014". Florència: Institute of Electrical and Electronics Engineers (IEEE), 2014, p. 1700-1704.