logo Idiap Research Institute        
Pranay Dighe
First name(s): Pranay
Last name(s): Dighe

Publications of Pranay Dighe
2020
2019
ANALYZING UNCERTAINTIES IN SPEECH RECOGNITION USING DROPOUT, Apoorv Vyas, Pranay Dighe, Sibo Tong and Hervé Bourlard, in: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019
2018
Far-field ASR Using Low-rank and Sparse Soft Targets from Parallel Data, Pranay Dighe, Hervé Bourlard and Afsaneh Asaei, in: IEEE Workshop on Spoken Language Technology, Athens, GREECE, pages 581-587, IEEE, 2018
attachment
2017
Low-rank and Sparse Soft Targets to Learn Better DNN Acoustic Models, Pranay Dighe, Afsaneh Asaei and Hervé Bourlard, in: Proceedings of 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2017), 2017
attachment
2016
Exploiting Low-dimensional Structures to Enhance DNN based Acoustic Modeling in Speech Recognition, Pranay Dighe, Gil Luyet, Afsaneh Asaei and Hervé Bourlard, in: Proceedings of 2016 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2016), Shanghai, pages 5690-5694, IEEE, 2016
attachment
Sparse Modeling of Neural Network Posterior Probabilities for Exemplar-based Speech Recognition, Pranay Dighe, Afsaneh Asaei and Hervé Bourlard, in: Speech Communication: Special Issue on Advances in Sparse Modeling and Low-rank Modeling for Speech Processing, 76:230–244, 2016
attachment
[DOI]
2015
Dictionary Learning for Sparse Representation of Neural Network Exemplars in Speech Recognition, Pranay Dighe, Afsaneh Asaei and Hervé Bourlard, in: Proceedings of SPARS 2015: Workshop on Signal Processing with Adaptive Sparse Structured Representations, 2015, pages 1093, 2015
attachment
Sparse Modeling of Neural Network Posterior Probabilities for Exemplar-Based Speech Recognition, Pranay Dighe, Afsaneh Asaei and Hervé Bourlard, in: Proceedings of SPARS 2015: Workshop on Signal Processing with Adaptive Sparse Structured Representations, 2015
attachment
2014
Modeling Overlapping Speech using Vector Taylor Series, Pranay Dighe, Marc Ferras and Hervé Bourlard, in: Odyssey: The Speaker and Language Recognition Workshop, Joensuu, Finland, 2014
attachment