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

This paper describes aneural blind source separation (BSS) method based on amortized
variational inference (AVI) of a non-linear generative model of mixture signals. A classical …

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 …

We propose a spatial loss for unsupervised multi-channel source separation. The proposed
loss exploits the duality of direction of arrival (DOA) and beamforming: the steering and …

We propose to learn surrogate functions of universal speech priors for determined blind
speech separation. Deep speech priors are highly desirable due to their superior modelling …

This paper presents an unsupervised multichannel method that can separate moving sound
sources based on an amortized variational inference (AVI) of joint separation and …

We present Self-Remixing, a novel self-supervised speech separation method, which refines
a pre-trained separation model in an unsupervised manner. Self-Remixing consists of a …

The selection of layers in the transfer learning fine‐tuning process ensures a pre‐trained
model's accuracy and adaptation in a new target domain. However, the selection process is …

A key challenge in machine learning is to generalize from training data to an application
domain of interest. This work extends the recently-proposed mixture invariant training (MixIT) …

This paper presents a weakly-supervised multichannel neural speech separation method for
distant speech recognition (DSR) of real conversational speech mixtures. A blind source …