Paper ID | MLSP-24.4 | ||
Paper Title | MULTI-DECODER DPRNN: SOURCE SEPARATION FOR VARIABLE NUMBER OF SPEAKERS | ||
Authors | Junzhe Zhu, Raymond Yeh, Mark Hasegawa-Johnson, University of Illinois at Urbana-Champaign, United States | ||
Session | MLSP-24: Applications in Audio and Speech Processing | ||
Location | Gather.Town | ||
Session Time: | Wednesday, 09 June, 16:30 - 17:15 | ||
Presentation Time: | Wednesday, 09 June, 16:30 - 17:15 | ||
Presentation | Poster | ||
Topic | Machine Learning for Signal Processing: [MLR-SSEP] Source separation | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | We propose an end-to-end trainable approach to single-channel speech separation with unknown number of speakers. Our approach extends the MulCat source separation backbone with additional output heads: a count-head to infer the number of speakers, and decoder-heads for reconstructing the original signals. Beyond the model, we also propose a metric on how to evaluate source separation with variable number of speakers. Specifically, we cleared up the issue on how to evaluate the quality when the ground-truth has more or less speakers than the ones predicted by the model. We evaluate our approach on the WSJ0-mix datasets, with mixtures up to five speakers. We demonstrate that our approach outperforms state-of-the-art in counting the number of speakers and remains competitive in quality of reconstructed signals. |