Using deep bidirectional recurrent neural networks for prosodic-target prediction in a unit-selection text-to-speech systemRaul FernandezAsaf Rendelet al.2015INTERSPEECH 2015
Score stabilization for speaker recognition trained on a small development setHagai Aronowitz2015INTERSPEECH 2015
Exploiting supervector structure for speaker recognition trained on a small development setHagai Aronowitz2015INTERSPEECH 2015
Investigating factor analysis features for deep neural networks in noisy speech recognitionSriram GanapathySamuel Thomaset al.2015INTERSPEECH 2015