18 citations · 58 across the 30 of their papers we have counts for
4 papers · 1 filter
Input Representation, Not Model Size or Pretraining Scale, Shapes Speaker Verification Robustness to Temporal Degradation
Erdem Baha Topbas, Srikanth Madikeri, Elisa Pellegrino +1
Speech remains intelligible to listeners under heavy temporal degradation, but whether speaker identity survives is largely unexplored. We evaluate six automatic speaker verificati…
Text-only adaptation in LLM-based ASR through text denoising
Andrés Carofilis, Sergio Burdisso, Esaú Villatoro-Tello +8
Adapting large language model (LLM)-based automatic speech recognition (ASR) systems to new domains using text-only data is a significant yet underexplored challenge. Standard fine…
Comparing CTC and LFMMI for out-of-domain adaptation of wav2vec 2.0 acoustic model
Apoorv Vyas, Srikanth Madikeri, Hervé Bourlard
In this work, we investigate if the wav2vec 2.0 self-supervised pretraining helps mitigate the overfitting issues with connectionist temporal classification (CTC) training to reduc…
Speech Activity Detection Based on Multilingual Speech Recognition System
Seyyed Saeed Sarfjoo, Srikanth Madikeri, Petr Motlicek
To better model the contextual information and increase the generalization ability of Speech Activity Detection (SAD) system, this paper leverages a multi-lingual Automatic Speech…