In reverberant conditions with multiple concurrent speakers, each microphone acquires a
mixture signal of multiple speakers at a different location. In over-determined conditions …

In reverberant conditions with a single speaker, each far-field microphone records a
reverberant version of the same speaker signal at a different location. In over-determined …

This paper proposes a domain adaptation method for speech enhancement called
Remixed2Remixed. The proposed method adopts Noise2Noise (N2N) learning to adapt …

Reverberation as supervision (RAS) is a framework that allows for training monaural speech
separation models from multi-channel mixtures in an unsupervised manner. In RAS, models …

This paper describes the NWPU-ByteAudio system for CHiME-7 Task 2-unsupervised
domain adaptation for conversational speech enhancement (UDASE). To better make use of …

We propose an unsupervised approach for training separation models from scratch using
RemixIT and Self-Remixing, which are recently proposed self-supervised learning methods …

RemixIT and Remixed2Remixed are domain adaptation-based speech enhancement
(DASE) methods that use a teacher model trained in full supervision to generate pseudo …

* Speech corpus compilation in the era of the internet.** Shinnosuke Takamichi (University
of Tokyo, Tokyo, 113–8656) e-mail: shinnosuke takamichi@ ipc. iutokyo. ac. jp [doi …