%Aigaion2 BibTeX export from Idiap Publications %Saturday 21 December 2024 05:20:25 PM @INPROCEEDINGS{Dey_ICASSP_2016, author = {Dey, Subhadeep and Madikeri, Srikanth and Ferras, Marc and Motlicek, Petr}, projects = {Idiap, SIIP}, month = mar, title = {DEEP NEURAL NETWORK BASED POSTERIORS FOR TEXT-DEPENDENT SPEAKER VERIFICATION}, booktitle = {Proceedings of 2016 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2016)}, year = {2016}, pages = {5050-5054}, publisher = {IEEE}, location = {Shanghai}, crossref = {Dey_Idiap-RR-08-2016}, abstract = {The i-vector and Joint Factor Analysis (JFA) systems for text- dependent speaker verification use sufficient statistics computed from a speech utterance to estimate speaker models. These statis- tics average the acoustic information over the utterance thereby losing all the sequence information. In this paper, we study ex- plicit content matching using Dynamic Time Warping (DTW) and present the best achievable error rates for speaker-dependent and speaker-independent content matching. For this purpose, a Deep Neural Network/Hidden Markov Model Automatic Speech Recog- nition (DNN/HMM ASR) system is used to extract content-related posterior probabilities. This approach outperforms systems using Gaussian mixture model posteriors by at least 50\% Equal Error Rate (EER) on the RSR2015 in content mismatch trials. DNN posteriors are also used in i-vector and JFA systems, obtaining EERs as low as 0.02\%.}, pdf = {https://publications.idiap.ch/attachments/papers/2016/Dey_ICASSP_2016.pdf} } crossreferenced publications: @TECHREPORT{Dey_Idiap-RR-08-2016, author = {Dey, Subhadeep and Madikeri, Srikanth and Ferras, Marc and Motlicek, Petr}, projects = {Idiap, SIIP}, month = {4}, title = {DEEP NEURAL NETWORK BASED POSTERIORS FOR TEXT-DEPENDENT SPEAKER VERIFICATION}, type = {Idiap-RR}, number = {Idiap-RR-08-2016}, year = {2016}, institution = {Idiap}, abstract = {The i-vector and Joint Factor Analysis (JFA) systems for text- dependent speaker verification use sufficient statistics computed from a speech utterance to estimate speaker models. These statis- tics average the acoustic information over the utterance thereby losing all the sequence information. In this paper, we study ex- plicit content matching using Dynamic Time Warping (DTW) and present the best achievable error rates for speaker-dependent and speaker-independent content matching. For this purpose, a Deep Neural Network/Hidden Markov Model Automatic Speech Recog- nition (DNN/HMM ASR) system is used to extract content-related posterior probabilities. This approach outperforms systems using Gaussian mixture model posteriors by at least 50\% Equal Error Rate (EER) on the RSR2015 in content mismatch trials. DNN posteriors are also used in i-vector and JFA systems, obtaining EERs as low as 0.02\%.}, pdf = {https://publications.idiap.ch/attachments/reports/2016/Dey_Idiap-RR-08-2016.pdf} }