activity
20192025
most citedSpeechBrain: A General-Purpose Speech Toolkit

514 citations · 519 across the 8 of their papers we have counts for

collaborators

11 papers

cs.SD2025

LibriVAD: A Scalable Open Dataset with Deep Learning Benchmarks for Voice Activity Detection

Ioannis Stylianou, Achintya kr. Sarkar, Nauman Dawalatabad +2

Robust Voice Activity Detection (VAD) remains a challenging task, especially under noisy, diverse, and unseen acoustic conditions. Beyond algorithmic development, a key limitation…

cs.SD2024

Automatic Prediction of Amyotrophic Lateral Sclerosis Progression using Longitudinal Speech Transformer

Liming Wang, Yuan Gong, Nauman Dawalatabad +7

Automatic prediction of amyotrophic lateral sclerosis (ALS) disease progression provides a more efficient and objective alternative than manual approaches. We propose ALS longitudi…

cs.CL2023

Improved Cross-Lingual Transfer Learning For Automatic Speech Translation

Sameer Khurana, Nauman Dawalatabad, Antoine Laurent +4

Research in multilingual speech-to-text translation is topical. Having a single model that supports multiple translation tasks is desirable. The goal of this work it to improve cro…

eess.AS2022

On Unsupervised Uncertainty-Driven Speech Pseudo-Label Filtering and Model Calibration

Nauman Dawalatabad, Sameer Khurana, Antoine Laurent +1

Pseudo-label (PL) filtering forms a crucial part of Self-Training (ST) methods for unsupervised domain adaptation. Dropout-based Uncertainty-driven Self-Training (DUST) proceeds by…

cs.SD2022★ 5 cited

Multi-stage Progressive Compression of Conformer Transducer for On-device Speech Recognition

Jash Rathod, Nauman Dawalatabad, Shatrughan Singh +1

The smaller memory bandwidth in smart devices prompts development of smaller Automatic Speech Recognition (ASR) models. To obtain a smaller model, one can employ the model compress…

eess.AS2022

Two-Pass End-to-End ASR Model Compression

Nauman Dawalatabad, Tushar Vatsal, Ashutosh Gupta +4

Speech recognition on smart devices is challenging owing to the small memory footprint. Hence small size ASR models are desirable. With the use of popular transducer-based models,…