Self-supervised speech pre-training methods have developed rapidly in recent years, which
show to be very effective for many near-field single-channel speech tasks. However, far-field …

When a sufficiently large far-field training data is presented, jointly optimizing a multichannel
frontend and an end-to-end (E2E) Automatic Speech Recognition (ASR) backend shows …

Voice Activity Detection (VAD) and Overlapped Speech Detection (OSD) are key pre-
processing tasks for speaker diarization. In the meeting context, it is often easier to capture …

Overlapped speech occurs when multiple speakers are simultaneously active. This may
lead to severe performance degradation in automatic speech processing systems such as …

Far-field automatic speech recognition (ASR) is a challenging task due to the background
noise and reverberation. To address this issue, we introduce a novel end-to-end multi …

With the development of teleconferencing and in-vehicle voice assistants, far-field multi-
speaker speech recognition has become a hot research topic. Recently, a multi-channel …

Ces travaux de thèse se concentrent sur le traitement automatique de la parole, et plus
particulièrement sur la diarisation en locuteurs. Cette tâche nécessite de segmenter le …

End-to-end (E2E) multi-channel ASR systems show state-of-the-art performance in far-field
ASR tasks by joint training of a multi-channel front-end along with the ASR model. The main …