Scholar
Saurabh Kataria
Google Scholar ID: z7kL9_IAAAAJ
Postdoctoral Fellow, Emory University
Citations & Impact
Citations
370
H-index
11
i10-index
12
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- 1. Journal pre-print 'Time-domain speech super-resolution with GAN based modeling for telephony speaker verification' under review; 2. 'Self-FiLM: Conditioning GANs with self-supervised representations for bandwidth extension based speaker recognition' published at INTERSPEECH 2023; 3. 'Advest: Adversarial perturbation estimation to classify and detect adversarial attacks against speaker identification' published at INTERSPEECH 2022; 4. 'Joint domain adaptation and speech bandwidth extension using time-domain GANs for speaker verification' published at INTERSPEECH 2022; 5. 'Defense against Adversarial Attacks on Hybrid Speech Recognition System using Adversarial Fine-tuning with Denoiser' published at INTERSPEECH 2022; 6. 'Advances in Cross-Lingual and Cross-Source Audio-Visual Speaker Recognition: The JHU-MIT System for NIST SRE21' published at Odyssey 2022; 7. 'Perceptual loss based speech denoising with an ensemble of audio pattern recognition and self-supervised models' published at ICASSP 202.
Research Experience
- 1. Interned at Tencent America with Dr. Shi-Xiong Zhang and Dr. Dong Yu; 2. Interned at INRIA with Dr. Antoine Deleforge; 3. Interned at New York University with Prof. Siddharth Garg; 4. During his Ph.D., he worked on deep learning-based speech enhancement and automatic speaker recognition, focusing on state-of-the-art effectiveness, speaker-identity preservation, and transfer learning.
Education
- Ph.D. in Electrical and Computer Engineering from Johns Hopkins University, advised by Prof. Najim Dehak and Prof. Jesús Villalba; Bachelor's and Master's degrees in Electrical Engineering from Indian Institute of Technology (IIT) Kanpur, advised by Prof. Tanaya Guha and Prof. Rajesh Hegde.
Background
- Currently a postdoctoral fellow at Emory Nursing AI in healthcare space, focusing on deep learning (self-supervised learning, multi-modal learning) and human language technology (speech processing, natural language processing).
Miscellany
- Personal interests not mentioned
Co-authors