Samuele Cornell

Dixtral achieves up to 29% absolute improvement in speaker-attributed transcription accuracy by leveraging diarization masks without risking catastrophic forgetting.

Exploiting noise inseparability allows for a breakthrough in weakly-supervised speech denoising, enhancing domain adaptability and performance without relying on clean targets.

Training speech separation models on real-world noisy data doesn't have to mean accepting noisy outputs: this method cuts residual noise in half.