Follow
Shrikant Venkataramani
Shrikant Venkataramani
Senior Research Scientist, Murf AI
Verified email at murf.ai
Title
Cited by
Cited by
Year
End-to-end source separation with adaptive front-ends
S Venkataramani, J Casebeer, P Smaragdis
Asilomar, 2018
832018
Two-step sound source separation: Training on learned latent targets
E Tzinis, S Venkataramani, Z Wang, C Subakan, P Smaragdis
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
742020
A neural network alternative to non-negative audio models
P Smaragdis, S Venkataramani
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
702017
Unsupervised deep clustering for source separation: Direct learning from mixtures using spatial information
E Tzinis, S Venkataramani, P Smaragdis
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
522019
Class-conditional embeddings for music source separation
P Seetharaman, G Wichern, S Venkataramani, J Le Roux
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
472019
Personalized percepnet: Real-time, low-complexity target voice separation and enhancement
R Giri, S Venkataramani, JM Valin, U Isik, A Krishnaswamy
arXiv preprint arXiv:2106.04129, 2021
422021
Adaptive front-ends for end-to-end source separation
S Venkataramani, J Casebeer, P Smaragdis
Proc. NIPS, 2017
402017
Self-supervised learning for speech enhancement
YC Wang, S Venkataramani, P Smaragdis
arXiv preprint arXiv:2006.10388, 2020
292020
Performance Based Cost Functions for End-to-End Speech Separation
S Venkataramani, R Higa, P Smaragdis
Asia-Pacific Signal and Information Processing Association Annual Summit and …, 2018
222018
Neural network alternatives to convolutive audio models for source separation
S Venkataramani, C Subakan, P Smaragdis
2017 IEEE 27th International Workshop on Machine Learning for Signal …, 2017
202017
End-to-end networks for supervised single-channel speech separation
S Venkataramani, P Smaragdis
arXiv preprint arXiv:1810.02568, 2018
102018
A style transfer approach to source separation
S Venkataramani, E Tzinis, P Smaragdis
2019 IEEE Workshop on Applications of Signal Processing to Audio and …, 2019
62019
Semi-supervised time domain target speaker extraction with attention
Z Wang, R Giri, S Venkataramani, U Isik, JM Valin, P Smaragdis, ...
arXiv preprint arXiv:2206.09072, 2022
52022
Efficient trainable front-ends for neural speech enhancement
J Casebeer, U Isik, S Venkataramani, A Krishnaswamy
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
52020
End-to-end non-negative autoencoders for sound source separation
S Venkataramani, E Tzinis, P Smaragdis
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
52020
Vocal Separation using Singer-Vowel Priors Obtained from Polyphonic Audio.
S Venkataramani, N Nayak, P Rao, R Velmurugan
ISMIR, 283-288, 2014
42014
To dereverb or not to dereverb? Perceptual studies on real-time dereverberation targets
JM Valin, R Giri, S Venkataramani, U Isik, A Krishnaswamy
arXiv preprint arXiv:2206.07917, 2022
32022
AutoDub: Automatic Redubbing for Voiceover Editing
S Venkataramani, P Smaragdis, G Mysore
Proceedings of the 30th Annual ACM Symposium on User Interface Software and …, 2017
12017
Improving mobile phone based query recognition with a microphone array
S Venkataramani, R Velmurugan, P Rao
2014 Twentieth National Conference on Communications (NCC), 1-6, 2014
12014
End-to-end non-negative auto-encoders: a deep neural alternative to non-negative audio modeling
S Venkataramani
2020
The system can't perform the operation now. Try again later.
Articles 1–20