Multi-Modal automatic speech recognition (ASR) techniques aim to leverage additional
modalities to improve the performance of speech recognition systems. While existing …

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 …

Hotword customization is one of the concerned issues remained in ASR field-it is of value to
enable users of ASR systems to customize names of entities, persons and other phrases to …

Contextualized end-to-end automatic speech recognition has been an active research area,
with recent efforts focusing on the implicit learning of contextual phrases based on the final …

Prompts are crucial to large language models as they provide context information such as
topic or logical relationships. Inspired by this, we propose PromptASR, a framework that …

The attention-based deep contextual biasing method has been demonstrated to effectively
improve the recognition performance of end-to-end automatic speech recognition (ASR) …

Contextual ASR or hotword customization holds substantial practical value. Despite the
impressive performance of current end-to-end (E2E) automatic speech recognition (ASR) …

End-to-end (E2E) automatic speech recognition (ASR) methods exhibit remarkable
performance. However, since the performance of such methods is intrinsically linked to the …

The growing prevalence of online conferences and courses presents a new challenge in
improving automatic speech recognition (ASR) with enriched textual information from video …

In this paper, we propose a Guided Attention (GA) auxiliary training loss, which improves the
effectiveness and robustness of automatic speech recognition (ASR) contextual biasing …