Automatic Speech Recognition (ASR) in conversational settings presents unique
challenges, including extracting relevant contextual information from previous …

Current ASR systems are mainly trained and evaluated at the utterance level. Long range
cross utterance context can be incorporated. A key task is to derive a suitable compact …

Deep biasing for the Transducer can improve the recognition performance of rare words or
contextual entities, which is essential in practical applications, especially for streaming …

Enhancing automatic speech recognition (ASR) performance by leveraging additional
multimodal information has shown promising results in previous studies. However, most of …

Recent dialogue systems rely on turn-based spoken interactions, requiring accurate
Automatic Speech Recognition (ASR). Errors in ASR can significantly impact downstream …

Self-supervised learning (SSL) based discrete speech representations are highly compact
and domain adaptable. In this paper, SSL discrete speech features extracted from WavLM …

With the advancement of Self-supervised Learning (SSL) in speech-related tasks, there has
been growing interest in utilizing discrete tokens generated by SSL for automatic speech …