E-LIB Suche - Ergebnisse für: Bourlard, Hervé

1

Autoencoders reloaded:

Bourlard, Hervé ; Kabil, Selen Hande
Biological Cybernetics. 116 (2022) 4 - p. 389-406 , 2022

Link: https://doi.org/10.1007/..

2

Lattice-Free Mmi Adaptation of Self-Supervised Pretrained A..:

, In: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Vyas, Apoorv ; Madikeri, Srikanth ; Bourlard, Herve - p. 6219-6223 , 2021

Link: https://doi.org/10.1109/..

3

Spectro-Temporal Sparsity Characterization for Dysarthric S..:

Kodrasi, Ina ; Bourlard, Herve
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 28 (2020) - p. 1210-1222 , 2020

Link: https://doi.org/10.1109/..

4

Neural Network Based End-to-End Query by Example Spoken Ter..:

Ram, Dhananjay ; Miculicich, Lesly ; Bourlard, Herve
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 28 (2020) - p. 1416-1427 , 2020

Link: https://doi.org/10.1109/..

5

Synthetic Speech References for Automatic Pathological Spee..:

, In: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Janbakhshi, Parvaneh ; Kodrasi, Ina ; Bourlard, Herve - p. 6099-6103 , 2020

Link: https://doi.org/10.1109/..

6

Incremental Semi-Supervised Learning for Multi-Genre Speech..:

, In: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Khonglah, Banriskhem ; Madikeri, Srikanth ; Dey, Subhadeep... - p. 7419-7423 , 2020

Link: https://doi.org/10.1109/..

7

On quantifying the quality of acoustic models in hybrid DNN..:

Dighe, Pranay ; Asaei, Afsaneh ; Bourlard, Hervé
Speech Communication. 119 (2020) - p. 24-35 , 2020

Link: https://doi.org/10.1016/..

8

Automatic Pathological Speech Intelligibility Assessment Ex..:

Janbakhshi, Parvaneh ; Kodrasi, Ina ; Bourlard, Herve
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 28 (2020) - p. 1717-1728 , 2020

Link: https://doi.org/10.1109/..

9

Pathological Speech Intelligibility Assessment Based on the..:

, In: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Janbakhshi, Parvaneh ; Kodrasi, Ina ; Bourlard, Herve - p. 6405-6409 , 2019

Link: https://doi.org/10.1109/..

10

Low-rank and sparse subspace modeling of speech for DNN bas..:

Dighe, Pranay ; Asaei, Afsaneh ; Bourlard, Hervé
Speech Communication. 109 (2019) - p. 34-45 , 2019

Link: https://doi.org/10.1016/..

11

Multilingual Bottleneck Features for Query by Example Spoke..:

, In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU),

Ram, Dhananjay ; Miculicich, Lesly ; Bourlard, Herve - p. 621-628 , 2019

Link: https://doi.org/10.1109/..

12

An End-to-end Network to Synthesize Intonation Using a Gene..:

, In: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Marelli, Francois ; Schnell, Bastian ; Bourlard, Herve.. - p. 7040-7044 , 2019

Link: https://doi.org/10.1109/..

13

Analyzing Uncertainties in Speech Recognition Using Dropout:

, In: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Vyas, Apoorv ; Dighe, Pranay ; Tong, Sibo. - p. 6730-6734 , 2019

Link: https://doi.org/10.1109/..

14

Super-gaussianity of Speech Spectral Coefficients as a Pote..:

, In: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Kodrasi, Ina ; Bourlard, Herve - p. 6400-6404 , 2019

Link: https://doi.org/10.1109/..

15

An Investigation of Multilingual ASR Using End-to-end LF-MM:

, In: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Tong, Sibo ; Garner, Philip N. ; Bourlard, Herve - p. 6061-6065 , 2019

Link: https://doi.org/10.1109/..