Deepak Baby

According to our database, Deepak Baby authored at least 19 papers between 2014 and 2022.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2022

Residual Adapters for Targeted Updates in RNN-Transducer Based Speech Recognition System.

Sungjun Han, Deepak Baby, Valentin Mendelev

Proceedings of the IEEE Spoken Language Technology Workshop, 2022

Incremental learning for RNN-Transducer based speech recognition models.

Deepak Baby, Pasquale D'Alterio, Valentin Mendelev

Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

2021

A convolutional neural-network model of human cochlear mechanics and filter tuning for real-time applications.

Deepak Baby, Arthur Van Den Broucke, Sarah Verhulst

Nat. Mach. Intell., 2021

Speech Dereverberation Using Variational Autoencoders.

Deepak Baby, Hervé Bourlard

Proceedings of the IEEE International Conference on Acoustics, 2021

2020

iSEGAN: Improved Speech Enhancement Generative Adversarial Networks.

Deepak Baby

CoRR, 2020

Hearing-Impaired Bio-Inspired Cochlear Models for Real-Time Auditory Applications.

Arthur Van Den Broucke, Deepak Baby, Sarah Verhulst

Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

2019

Sergan: Speech Enhancement Using Relativistic Generative Adversarial Networks with Gradient Penalty.

Deepak Baby, Sarah Verhulst

Proceedings of the IEEE International Conference on Acoustics, 2019

2018

Machines hear better when they have ears.

Deepak Baby, Sarah Verhulst

CoRR, 2018

Biophysically-inspired Features Improve the Generalizability of Neural Network-based Speech Enhancement Systems.

Deepak Baby, Sarah Verhulst

Proceedings of the 19th Annual Conference of the International Speech Communication Association, 2018

2017

Joint Denoising and Dereverberation Using Exemplar-Based Sparse Representations and Decaying Norm Constraint.

Deepak Baby, Hugo Van hamme

IEEE ACM Trans. Audio Speech Lang. Process., 2017

2016

Supervised speech dereverberation in noisy environments using exemplar-based sparse representations.

Deepak Baby, Hugo Van hamme

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

2015

Coupled Dictionaries for Exemplar-Based Speech Enhancement and Automatic Speech Recognition.

Deepak Baby, Tuomas Virtanen, Jort F. Gemmeke, Hugo Van hamme

IEEE ACM Trans. Audio Speech Lang. Process., 2015

Noise robust exemplar matching for speech enhancement: applications to automatic speech recognition.

Emre Yilmaz, Deepak Baby, Hugo Van hamme

Proceedings of the 16th Annual Conference of the International Speech Communication Association, 2015

Investigating modulation spectrogram features for deep neural network-based automatic speech recognition.

Deepak Baby, Hugo Van hamme

Proceedings of the 16th Annual Conference of the International Speech Communication Association, 2015

Exemplar-based speech enhancement for deep neural network based automatic speech recognition.

Deepak Baby, Jort F. Gemmeke, Tuomas Virtanen, Hugo Van hamme

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

Noise robust exemplar matching with coupled dictionaries for single-channel speech enhancement.

Emre Yilmaz, Deepak Baby, Hugo Van hamme

Proceedings of the 23rd European Signal Processing Conference, 2015

Hybrid input spaces for exemplar-based noise robust speech recognition using coupled dictionaries.

Deepak Baby, Hugo Van hamme

Proceedings of the 23rd European Signal Processing Conference, 2015

2014

Exemplar-based noise robust automatic speech recognition using modulation spectrogram features.

Deepak Baby, Tuomas Virtanen, Jort F. Gemmeke, Tom Barker, Hugo Van hamme

Proceedings of the 2014 IEEE Spoken Language Technology Workshop, 2014

Coupled dictionary training for exemplar-based speech enhancement.

Deepak Baby, Tuomas Virtanen, Tom Barker, Hugo Van hamme

Proceedings of the IEEE International Conference on Acoustics, 2014