3 citations · 8 across the 11 of their papers we have counts for
14 papers · 1 filter
Self-FiLM: Conditioning GANs with self-supervised representations for bandwidth extension based speaker recognition
Saurabh Kataria, Jesús Villalba, Laureano Moro-Velázquez +2
Speech super-resolution/Bandwidth Extension (BWE) can improve downstream tasks like Automatic Speaker Verification (ASV). We introduce a simple novel technique called Self-FiLM to…
Time-domain speech super-resolution with GAN based modeling for telephony speaker verification
Saurabh Kataria, Jesús Villalba, Laureano Moro-Velázquez +2
Automatic Speaker Verification (ASV) technology has become commonplace in virtual assistants. However, its performance suffers when there is a mismatch between the train and test d…
Defense against Adversarial Attacks on Hybrid Speech Recognition using Joint Adversarial Fine-tuning with Denoiser
Sonal Joshi, Saurabh Kataria, Yiwen Shao +4
Adversarial attacks are a threat to automatic speech recognition (ASR) systems, and it becomes imperative to propose defenses to protect them. In this paper, we perform experiments…
AdvEst: Adversarial Perturbation Estimation to Classify and Detect Adversarial Attacks against Speaker Identification
Sonal Joshi, Saurabh Kataria, Jesus Villalba +1
Adversarial attacks pose a severe security threat to the state-of-the-art speaker identification systems, thereby making it vital to propose countermeasures against them. Building…
Joint domain adaptation and speech bandwidth extension using time-domain GANs for speaker verification
Saurabh Kataria, Jesús Villalba, Laureano Moro-Velázquez +1
Speech systems developed for a particular choice of acoustic domain and sampling frequency do not translate easily to others. The usual practice is to learn domain adaptation and b…
Deep Feature CycleGANs: Speaker Identity Preserving Non-parallel Microphone-Telephone Domain Adaptation for Speaker Verification
Saurabh Kataria, Jesús Villalba, Piotr Żelasko +2
With the increase in the availability of speech from varied domains, it is imperative to use such out-of-domain data to improve existing speech systems. Domain adaptation is a prom…
Perceptual Loss based Speech Denoising with an ensemble of Audio Pattern Recognition and Self-Supervised Models
Saurabh Kataria, Jesús Villalba, Najim Dehak
Deep learning based speech denoising still suffers from the challenge of improving perceptual quality of enhanced signals. We introduce a generalized framework called Perceptual En…
Multi-Channel Speaker Verification for Single and Multi-talker Speech
Saurabh Kataria, Shi-Xiong Zhang, Dong Yu
To improve speaker verification in real scenarios with interference speakers, noise, and reverberation, we propose to bring together advancements made in multi-channel speech featu…
Single Channel Far Field Feature Enhancement For Speaker Verification In The Wild
Phani Sankar Nidadavolu, Saurabh Kataria, Paola García-Perera +2
We investigated an enhancement and a domain adaptation approach to make speaker verification systems robust to perturbations of far-field speech. In the enhancement approach, using…
Analysis of Deep Feature Loss based Enhancement for Speaker Verification
Saurabh Kataria, Phani Sankar Nidadavolu, Jesús Villalba +1
Data augmentation is conventionally used to inject robustness in Speaker Verification systems. Several recently organized challenges focus on handling novel acoustic environments.…
Speaker detection in the wild: Lessons learned from JSALT 2019
Paola Garcia, Jesus Villalba, Herve Bredin +21
This paper presents the problems and solutions addressed at the JSALT workshop when using a single microphone for speaker detection in adverse scenarios. The main focus was to tack…
Low-Resource Domain Adaptation for Speaker Recognition Using Cycle-GANs
Phani Sankar Nidadavolu, Saurabh Kataria, Jesús Villalba +1
Current speaker recognition technology provides great performance with the x-vector approach. However, performance decreases when the evaluation domain is different from the traini…
Unsupervised Feature Enhancement for speaker verification
Phani Sankar Nidadavolu, Saurabh Kataria, Jesús Villalba +2
The task of making speaker verification systems robust to adverse scenarios remain a challenging and an active area of research. We developed an unsupervised feature enhancement ap…
Feature Enhancement with Deep Feature Losses for Speaker Verification
Saurabh Kataria, Phani Sankar Nidadavolu, Jesús Villalba +3
Speaker Verification still suffers from the challenge of generalization to novel adverse environments. We leverage on the recent advancements made by deep learning based speech enh…