Large language models (LLMs) are increasingly recognized for their advanced language
capabilities, offering significant assistance in diverse areas like medical communication …

Advancements in deep neural networks have allowed automatic speech recognition (ASR)
systems to attain human parity on several publicly available clean speech datasets …

The integration of natural language processing (NLP) technologies into educational
applications has shown promising results, particularly in the language learning domain …

In this paper, we propose WavePurifier, an audio purification framework to defend against
audio adversarial attacks. Audio adversarial attacks craft adversarial examples or …

Speech recognition technology has improved recently. However, in the context of spoken
language understanding (SLU), containing automatic speech recognition (ASR) errors …

Despite significant advances in automatic speech recognition (ASR) accuracy, challenges
remain. Naturally occurring conversation often involves multiple overlap** speakers, of …

This paper investigates an approach for adapting RNN-Transducer (RNN-T) based
automatic speech recognition (ASR) model to improve the recognition of unseen words …

End-to-end automatic speech recognition (E2E ASR) systems often suffer from
mistranscription of domain-specific phrases, such as named entities, sometimes leading to …

In various academic and professional settings, such as mathematics lectures or research
presentations, it is often necessary to convey mathematical expressions orally. However …

Accurately finding the wrong words in the automatic speech recognition (ASR) hypothesis
and recovering them well-founded is the goal of speech error correction. In this paper, we …