Follow
Saurabh Kataria
Saurabh Kataria
Other namesसौरभ कटारिया
Postdoc Fellow, Emory University
Verified email at emory.edu - Homepage
Title
Cited by
Cited by
Year
Perceptual loss based speech denoising with an ensemble of audio pattern recognition and self-supervised models
S Kataria, J Villalba, N Dehak
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
412021
Feature enhancement with deep feature losses for speaker verification
S Kataria, PS Nidadavolu, J Villalba, N Chen, P Garcia-Perera, N Dehak
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
382020
Speaker detection in the wild: Lessons learned from JSALT 2019
P García, J Villalba, H Bredin, J Du, D Castan, A Cristia, L Bullock, L Guo, ...
arXiv preprint arXiv:1912.00938, 2019
372019
Low-resource domain adaptation for speaker recognition using cycle-gans
PS Nidadavolu, S Kataria, J Villalba, N Dehak
2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2019
292019
Unsupervised feature enhancement for speaker verification
PS Nidadavolu, S Kataria, J Villalba, P Garcia-Perera, N Dehak
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
222020
Advances in Speaker Recognition for Telephone and Audio-Visual Data: the JHU-MIT Submission for NIST SRE19
J Villalba, D Garcia-Romero, N Chen, G Sell, J Borgstrom, A McCree, ...
212020
Analysis of deep feature loss based enhancement for speaker verification
S Kataria, PS Nidadavolu, J Villalba, N Dehak
arXiv preprint arXiv:2002.00139, 2020
172020
VAST: The virtual acoustic space traveler dataset
C Gaultier, S Kataria, A Deleforge
Latent Variable Analysis and Signal Separation: 13th International …, 2017
172017
Hearing in a shoe-box: binaural source position and wall absorption estimation using virtually supervised learning
S Kataria, C Gaultier, A Deleforge
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
132017
Deep feature cyclegans: Speaker identity preserving non-parallel microphone-telephone domain adaptation for speaker verification
S Kataria, J Villalba, P Żelasko, L Moro-Velázquez, N Dehak
arXiv preprint arXiv:2104.01433, 2021
122021
Advest: Adversarial perturbation estimation to classify and detect adversarial attacks against speaker identification
S Joshi, S Kataria, J Villalba, N Dehak
arXiv preprint arXiv:2204.03848, 2022
82022
Defense against Adversarial Attacks on Hybrid Speech Recognition System using Adversarial Fine-tuning with Denoiser
S Joshi, S Kataria, Y Shao, P Żelasko, J Villalba, S Khudanpur, N Dehak
Proc. Interspeech 2022, 2022
8*2022
Advances in Cross-Lingual and Cross-Source Audio-Visual Speaker Recognition: The JHU-MIT System for NIST SRE21.
J Villalba, BJ Borgstrom, S Kataria, M Rybicka, CD Castillo, J Cho, ...
Odyssey, 213-220, 2022
72022
Dictionary learning based applications in image processing using convex optimisation
A Kumar, S Kataria
Int. Conf. on Signal Processing and Integrated Networks (SPIN), Noida, India, 2017
72017
Joint domain adaptation and speech bandwidth extension using time-domain GANs for speaker verification
S Kataria, J Villalba, L Moro-Velázquez, N Dehak
arXiv preprint arXiv:2203.16614, 2022
52022
Single channel far field feature enhancement for speaker verification in the wild
PS Nidadavolu, S Kataria, P García-Perera, J Villalba, N Dehak
arXiv preprint arXiv:2005.08331, 2020
52020
The jhu-mit system description for nist sre19 av
J Villalba, D Garcia-Romero, N Chen, G Sell, J Borgstrom, A McCree, ...
NIST SRE19 Workshop, 2019
42019
Advances in Speaker Recognition for Multilingual Conversational Telephone Speech: The JHU-MIT System for NIST SRE20 CTS Challenge.
J Villalba, BJ Borgstrom, S Kataria, J Cho, PA Torres-Carrasquillo, ...
Odyssey, 338-345, 2022
32022
Multi-Channel Speaker Verification for Single and Multi-talker Speech
S Kataria, SX Zhang, D Yu
Interspeech 2021, 2021
32021
Time-domain speech super-resolution with gan based modeling for telephony speaker verification
S Kataria, J Villalba, L Moro-Velázquez, P Żelasko, N Dehak
IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2024
22024
The system can't perform the operation now. Try again later.
Articles 1–20