Recently, the speech community is seeing a significant trend of moving from deep neural
network based hybrid modeling to end-to-end (E2E) modeling for automatic speech …

Recent advancements in deep learning (DL) have posed a significant challenge for
automatic speech recognition (ASR). ASR relies on extensive training datasets, including …

The evaluation campaign of the 19th International Conference on Spoken Language
Translation featured eight shared tasks:(i) Simultaneous speech translation,(ii) Offline …

Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as
quickly and accurately as possible, while full-context ASR waits for the completion of a full …

Examination of speech datasets for detecting dementia, collected via various speech tasks,
has revealed links between speech and cognitive abilities. However, the speech dataset …

We live in a world where 60% of the population can speak two or more languages fluently.
Members of these communities constantly switch between languages when having a …

End-to-end simultaneous speech translation (SST), which directly translates speech in one
language into text in another language in real-time, is useful in many scenarios but has not …

We introduce a new approach for speech pre-training named SPIRAL which works by
learning denoising representation of perturbed data in a teacher-student framework …

In real-world applications, users often require both translations and transcriptions of speech
to enhance their comprehension, particularly in streaming scenarios where incremental …

Optimization of modern ASR architectures is among the highest priority tasks since it saves
many computational resources for model training and inference. The work proposes a new …