Thilo von Neumann

TL;DR: In this paper, an all-neural approach to simultaneous speaker counting, diarization and source separation is presented, where the neural network is recurrent over time as well as over the number of sources.

TL;DR: In this article, a Convolutional Time Domain Audio Separation Network (Conv-TasNet) is combined with an end-to-end speech recognizer and trained jointly by distributing it over multiple GPUs or approximating truncated back-propagation for the convolutional front-end.

TL;DR: This paper presents for the first time an all-neural approach to simultaneous speaker counting, diarization and source separation, using an NN-based estimator that operates in a block-online fashion and tracks speakers even if they remain silent for a number of time blocks, thus learning a stable output order for the separated sources.

TL;DR: This model structure improves the signal to distortion ratio (SDR) over a DAN baseline and provides up to 61% and up to 34% relative reduction in permutation error rate and re-identification error rate compared to an i-vector baseline, respectively.

TL;DR: In this article, an iterative speech extraction system with mechanisms to count the number of sources and combine it with a single-talker speech recognizer to form the first end-to-end multi-talkers automatic speech recognition system for an unknown number of active speakers.