Files in this item

FilesDescriptionFormat

application/pdf

application/pdfFA20-ECE499-Thesis-Zhu Junzhe.pdf (215kB)
(no description provided)PDF

Description

Title:Multi-decoder DPRNN high accuracy source counting and separation
Author(s):Junzhe, Zhu
Contributor(s):Hasegawa-Johnson, Mark
Subject(s):source separation
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.
Issue Date:2020-12
Genre:Other
Type:Text
Language:English
URI:http://hdl.handle.net/2142/109201
Date Available in IDEALS:2021-01-15


This item appears in the following Collection(s)

Item Statistics