We study the capabilities of speech processing systems trained simply to predict large
amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual …

As Automatic Speech Processing (ASR) systems are getting better, there is an increasing
interest of using the ASR output to do downstream Natural Language Processing (NLP) …

Conformer-based models have become the dominant end-to-end architecture for speech
processing tasks. With the objective of enhancing the conformer architecture for efficient …

We introduce AudioBench, a universal benchmark designed to evaluate Audio Large
Language Models (AudioLLMs). It encompasses 8 distinct tasks and 26 datasets, among …

Recent advances in speech recognition and translation rely on hundreds of thousands of
hours of Internet speech data. We argue that state-of-the art accuracy can be reached …

Collecting sufficient labeled data for spoken language understanding (SLU) is expensive
and time-consuming. Recent studies achieved promising results by using pre-trained …

Continuous speech separation using a microphone array was shown to be promising in
dealing with the speech overlap problem in natural conversation transcription. This paper …

End-to-end spoken language understanding (SLU) systems are gaining popularity over
cascaded approaches due to their simplicity and ability to avoid error propagation. However …

End-to-end automatic speech recognition suffers from adaptation to unknown target domain
speech despite being trained with a large amount of paired audio--text data. Recent studies …

Contextual ASR, which takes a list of bias terms as input along with audio, has drawn recent
interest as ASR use becomes more widespread. We are releasing contextual biasing lists to …