When labeled data is insufficient, pseudo-labeling based semi-supervised learning can
significantly improve the performance of automatic speech recognition. However, pseudo …

Modern speech recognition systems exhibit rapid performance degradation under domain
shift. This issue is especially prevalent in data-scarce settings, such as low-resource …

Quantum state verification (QSV) is the task of relying on local measurements only to verify
that a given quantum device does produce the desired target state. Up to now, certain types …

We propose an unsupervised adaptation framework, Self-TAught Recognizer (STAR), which
leverages unlabeled data to enhance the robustness of automatic speech recognition (ASR) …

The performance of automatic speech recognition (ASR) models has been significantly
improved owing to advances in deep learning and end-to-end approaches. However, these …

State-of-the-art models like OpenAI's Whisper exhibit strong performance in multilingual
automatic speech recognition (ASR), but they still face challenges in accurately recognizing …

Adapting Automatic Speech Recognition (ASR) models to new domains leads to
Catastrophic Forgetting (CF) of previously learned information. This paper addresses CF in …

Unsupervised domain adaptation (UDA) aims to improve the cross-domain model
performance without labeled target domain data. Distribution matching is a widely used UDA …

In the recent years, a dominant strategy has arised in machine learning, ie, scaling-up model
capacity and training data, with impressive results. However, the development of techniques …