Audio is an essential part of our life, but creating it often requires expertise and is time-
consuming. Research communities have made great progress over the past year advancing …

The detection and localization of highly realistic deepfake audio-visual content are
challenging even for the most advanced state-of-the-art methods. While most of the research …

Until recently, the field of speaker diarization was dominated by cascaded systems. Due to
their limitations, mainly regarding overlapped speech and cumbersome pipelines, end-to …

Speech-to-text services aim to transcribe input audio as accurately as possible. They
increasingly play a role in everyday life, for example in personal voice assistants or in …

The detection and localization of deepfake content, particularly when small fake segments
are seamlessly mixed with real videos, remains a significant challenge in the field of digital …

Recently, speech generation models have made significant progress by using large-scale
training data. However, the research community struggle to produce highly spontaneous …

This technical report describes the submission of team pyannote to the VoxSRC 2023
speaker diarization challenge. It relies on 3 stages: local end-to-end neural speaker …

In recent years, speech generation has seen remarkable progress, now achieving one-shot
generation capability that is often virtually indistinguishable from real human voice …

This paper describes the submissions of team TalTech-IRIT-LIS to the DISPLACE 2024
challenge. Our team participated in the speaker diarization and language diarization tracks …

A major drawback of supervised speech separation (SSep) systems is their reliance on
synthetic data, leading to poor real-world generalization. Mixture invariant training (MixIT) …