Seguir
Deepak Baby
Título
Citado por
Citado por
Ano
Sergan: Speech enhancement using relativistic generative adversarial networks with gradient penalty
D Baby, S Verhulst
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
1152019
A convolutional neural-network model of human cochlear mechanics and filter tuning for real-time applications
D Baby, A Van Den Broucke, S Verhulst
Nature machine intelligence 3 (2), 134-143, 2021
422021
Coupled dictionaries for exemplar-based speech enhancement and automatic speech recognition
D Baby, T Virtanen, JF Gemmeke
IEEE/ACM transactions on audio, speech, and language processing 23 (11 …, 2015
422015
Exemplar-based speech enhancement for deep neural network based automatic speech recognition
D Baby, J Gemmeke, T Virtanen, H Van hamme
IEEE ICASSP 2015, 2015
242015
Coupled dictionary training for exemplar-based speech enhancement
D Baby, T Virtanen, T Barker, H Van hamme
Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International …, 2014
242014
A convolutional neural-network framework for modelling auditory sensory cells and synapses
F Drakopoulos, D Baby, S Verhulst
Communications Biology 4 (1), 827, 2021
212021
Biophysically-inspired features improve the generalizability of neural network-based speech enhancement systems
D Baby, S Verhulst
INTERSPEECH, 2018
162018
Ordered Orthogonal Matching Pursuit
D Baby, SRB Pillai
Communications (NCC), 2012 National Conference on, 2012
13*2012
Real-time audio processing on a Raspberry Pi using deep neural networks
F Drakopoulos, D Baby, S Verhulst
23rd International Congress on Acoustics (ICA 2019), 2827-2834, 2019
122019
Joint Denoising and Dereverberation Using Exemplar-Based Sparse Representations and Decaying Norm Constraint
D Baby, H Van hamme
IEEE/ACM Transactions on Audio, Speech, and Language Processing 25 (10 …, 2017
112017
Supervised speech dereverberation in noisy environments using exemplar-based sparse representations
D Baby, H Van hamme
Accoustics, Speech and Signal Processing, 2016 IEEE International Conference on, 2016
112016
Investigating modulation spectrogram features for deep neural network-based automatic speech recognition
D Baby, H Van hamme
Proceedings Interspeech 2015, 2479-2483, 2015
92015
Hearing-impaired bio-inspired cochlear models for real-time auditory applications
A Van Den Broucke, D Baby, S Verhulst
21st Annual Conference of the International Speech Communication Association …, 2020
82020
isegan: Improved speech enhancement generative adversarial networks
D Baby
arXiv preprint arXiv:2002.08796, 2020
72020
Incremental learning for RNN-Transducer based speech recognition models
D Baby, P D'Alterio, V Mendelev
62022
Exemplar-based noise robust automatic speech recognition using modulation spectrogram features
D Baby, T Virtanen, J Gemmeke, T Barker, H Van hamme
Proceedings SLT 2014, 1-6, 2014
62014
Automated speech analysis to improve TMS-based language mapping: Algorithm and proof of concept
L Seynaeve, D Baby, S De Vleeschouwer, P Dupont, W Van Paesschen
Brain Stimulation: Basic, Translational, and Clinical Research in …, 2020
52020
Speech dereverberation using variational autoencoders
D Baby, H Bourlard
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
42021
NEURAL NETWORK MODEL FOR COCHLEAR MECHANICS AND PROCESSING
D Baby, S Verhulst, F Drakpoulos, A Van Den Broucke
US Patent US 11,800,301, 2023
3*2023
Residual adapters for targeted updates in rnn-transducer based speech recognition system
S Han, D Baby, V Mendelev
2022 IEEE Spoken Language Technology Workshop (SLT), 160-166, 2023
32023
O sistema não pode efectuar a operação agora. Tente mais tarde.
Artigos 1–20