5 citations · 6 across the 3 of their papers we have counts for
4 papers
Improving Low-Resource Speech Recognition with Pretrained Speech Models: Continued Pretraining vs. Semi-Supervised Training
Mitchell DeHaven, Jayadev Billa
Self-supervised Transformer based models, such as wav2vec 2.0 and HuBERT, have produced significant improvements over existing approaches to automatic speech recognition (ASR). Thi…
Attack-Agnostic Adversarial Detection
Jiaxin Cheng, Mohamed Hussein, Jay Billa +1
The growing number of adversarial attacks in recent years gives attackers an advantage over defenders, as defenders must train detectors after knowing the types of attacks, and man…
Improving low-resource ASR performance with untranscribed out-of-domain data
Jayadev Billa
Semi-supervised training (SST) is a common approach to leverage untranscribed/unlabeled speech data to improve automatic speech recognition performance in low-resource languages. H…
Improving LSTM-CTC based ASR performance in domains with limited training data
Jayadev Billa
This paper addresses the observed performance gap between automatic speech recognition (ASR) systems based on Long Short Term Memory (LSTM) neural networks trained with the connect…