CONF BenZeghiba_eurospeech-03/IDIAP On the Combination of Speech and Speaker Recognition BenZeghiba, Mohamed Faouzi Bourlard, Hervé EXTERNAL https://publications.idiap.ch/attachments/reports/2003/rr03-19.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/benzeghiba-03-19 Related documents European Conference On Speech, Communication and Technology (EUROSPEECH'03) 2003 Geneva, Switzerland 1361-1364 IDIAP-RR 03-19 This paper investigates an approach that maximizes the joint posterior probabil ity of the pronounced word and the speaker identity given the observed data. This probability can be expressed as a product of the posterior probability of the pronounced word estimated through an artificial neural network (ANN,',','), and the likelihood of the data estimated through a Gaussian mixture model (GMM). We show that the posterior probabilities estimated through a speaker-dependent ANN, as usually done in the hybrid HMM/ANN systems, are reliable for speech recognition but they are less reliable for speaker recognition. To alleviate this problem, we thus study how this posterior probability can be combined with the likelihood derived from a speaker-dependent GMM model to improve the speaker recognition performance. We thus end up with a joint model that can be used for text-dependent speaker identification and for speech recognition (and mutually benefiting from each other). REPORT BenZeghiba-03-19/IDIAP On the Combination of Speech and Speaker Recognition BenZeghiba, Mohamed Faouzi Bourlard, Hervé EXTERNAL https://publications.idiap.ch/attachments/reports/2003/rr03-19.pdf PUBLIC Idiap-RR-19-2003 2003 IDIAP in Proceedings of the 8th European Conference on Speech,Communication and Technology (EUROSPEECH'03) This paper investigates an approach that maximizes the joint posterior probabil ity of the pronounced word and the speaker identity given the observed data. This probability can be expressed as a product of the posterior probability of the pronounced word estimated through an artificial neural network (ANN,',','), and the likelihood of the data estimated through a Gaussian mixture model (GMM). We show that the posterior probabilities estimated through a speaker-dependent ANN, as usually done in the hybrid HMM/ANN systems, are reliable for speech recognition but they are less reliable for speaker recognition. To alleviate this problem, we thus study how this posterior probability can be combined with the likelihood derived from a speaker-dependent GMM model to improve the speaker recognition performance. We thus end up with a joint model that can be used for text-dependent speaker identification and for speech recognition (and mutually benefiting from each other).