56 citations · 206 across the 12 of their papers we have counts for
5 papers · 1 filter
End-to-end training of time domain audio separation and recognition
Thilo von Neumann, Keisuke Kinoshita, Lukas Drude +4
The rising interest in single-channel multi-speaker speech separation sparked development of End-to-End (E2E) approaches to multi-speaker speech recognition. However, up until now,…
Demystifying TasNet: A Dissecting Approach
Jens Heitkaemper, Darius Jakobeit, Christoph Boeddeker +2
In recent years time domain speech separation has excelled over frequency domain separation in single channel scenarios and noise-free environments. In this paper we dissect the ga…
SMS-WSJ: Database, performance measures, and baseline recipe for multi-channel source separation and recognition
Lukas Drude, Jens Heitkaemper, Christoph Boeddeker +1
We present a multi-channel database of overlapping speech for training, evaluation, and detailed analysis of source separation and extraction algorithms: SMS-WSJ -- Spatialized Mul…
Unsupervised training of neural mask-based beamforming
Lukas Drude, Jahn Heymann, Reinhold Haeb-Umbach
We present an unsupervised training approach for a neural network-based mask estimator in an acoustic beamforming application. The network is trained to maximize a likelihood crite…
Unsupervised training of a deep clustering model for multichannel blind source separation
Lukas Drude, Daniel Hasenklever, Reinhold Haeb-Umbach
We propose a training scheme to train neural network-based source separation algorithms from scratch when parallel clean data is unavailable. In particular, we demonstrate that an…