4 accepted papers
Although state-of-the-art Speech Foundational Models can produce high-quality text pseudo-labels, applying Semi-Supervised Learning (SSL) for in-the-wild real-world data remains challenging due to its richer and more complex acoustics compared to curated datasets. To address the challenges, we intro…
In recent years, there has been a growing interest in designing small-footprint yet effective Connectionist Temporal Classification based keyword spotting (CTC-KWS) systems. They are typically deployed on low-resource computing platforms, where limitations on model size and computational capacity cr…
Noisy Student Training (NST) has recently demonstrated extremely strong performance in Automatic Speech Recognition (ASR). In this paper, we propose a data selection strategy named LM Filter to improve the performance of NST on non-target domain data in ASR tasks. Hypotheses with and without a Langu…
Deep neural network (DNN) has achieved the state-of-the-art performance in automatic speech recognition (ASR). However, the meaning of parameters and neurons are hard to be interpreted in DNNs, which makes the regularizations and adaptation of DNNs difficult. In this work, we aim to do effective and…