Mirco Ravanelli
Mirco Ravanelli
Université de Montréal - MILA
Geverifieerd e-mailadres voor fbk.eu - Homepage
Titel
Geciteerd door
Geciteerd door
Jaar
Speaker recognition from raw waveform with sincnet
M Ravanelli, Y Bengio
2018 IEEE Spoken Language Technology Workshop (SLT), 1021-1028, 2018
2712018
Light gated recurrent units for speech recognition
M Ravanelli, P Brakel, M Omologo, Y Bengio
IEEE Transactions on Emerging Topics in Computational Intelligence 2 (2), 92-102, 2018
1292018
The pytorch-kaldi speech recognition toolkit
M Ravanelli, T Parcollet, Y Bengio
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
1112019
Learning problem-agnostic speech representations from multiple self-supervised tasks
S Pascual, M Ravanelli, J Serra, A Bonafonte, Y Bengio
arXiv preprint arXiv:1904.03416, 2019
912019
Speech model pre-training for end-to-end spoken language understanding
L Lugosch, M Ravanelli, P Ignoto, VS Tomar, Y Bengio
arXiv preprint arXiv:1904.03670, 2019
882019
The DIRHA simulated corpus.
L Cristoforetti, M Ravanelli, M Omologo, A Sosi, A Abad, M Hagmüller, ...
LREC, 2629-2634, 2014
822014
Quaternion recurrent neural networks
T Parcollet, M Ravanelli, M Morchid, G Linarès, C Trabelsi, R De Mori, ...
arXiv preprint arXiv:1806.04418, 2018
592018
Multi-task self-supervised learning for robust speech recognition
M Ravanelli, J Zhong, S Pascual, P Swietojanski, J Monteiro, J Trmal, ...
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
562020
Interpretable convolutional filters with sincnet
M Ravanelli, Y Bengio
arXiv preprint arXiv:1811.09725, 2018
542018
Improving speech recognition by revising gated recurrent units
M Ravanelli, P Brakel, M Omologo, Y Bengio
arXiv preprint arXiv:1710.00641, 2017
482017
The DIRHA-English corpus and related tasks for distant-speech recognition in domestic environments
M Ravanelli, L Cristoforetti, R Gretter, M Pellin, A Sosi, M Omologo
2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU …, 2015
472015
Learning speaker representations with mutual information
M Ravanelli, Y Bengio
arXiv preprint arXiv:1812.00271, 2018
392018
A network of deep neural networks for distant speech recognition
M Ravanelli, P Brakel, M Omologo, Y Bengio
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
392017
Realistic multi-microphone data simulation for distant speech recognition
M Ravanelli, P Svaizer, M Omologo
arXiv preprint arXiv:1711.09470, 2017
362017
Audio concept classification with hierarchical deep neural networks
M Ravanelli, B Elizalde, K Ni, G Friedland
2014 22nd European Signal Processing Conference (EUSIPCO), 606-610, 2014
322014
Impulse response estimation for robust speech recognition in a reverberant environment
M Ravanelli, A Sosi, P Svaizer, M Omologo
2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO …, 2012
312012
Batch-normalized joint training for DNN-based distant speech recognition
M Ravanelli, P Brakel, M Omologo, Y Bengio
2016 IEEE Spoken Language Technology Workshop (SLT), 28-34, 2016
302016
Contaminated speech training methods for robust DNN-HMM distant speech recognition
M Ravanelli, M Omologo
arXiv preprint arXiv:1710.03538, 2017
232017
The DIRHA-GRID corpus: baseline and tools for multi-room distant speech recognition using distributed microphones
M Matassoni, RF Astudillo, A Katsamanis, M Ravanelli
Fifteenth Annual Conference of the International Speech Communication …, 2014
222014
On the selection of the impulse responses for distant-speech recognition based on contaminated speech training
M Ravanelli, M Omologo
Fifteenth Annual Conference of the International Speech Communication …, 2014
212014
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–20