Many-Speakers Single Channel Speech Separation with Optimal Permutation Training

04/18/2021
by   Shaked Dovrat, et al.
0

Single channel speech separation has experienced great progress in the last few years. However, training neural speech separation for a large number of speakers (e.g., more than 10 speakers) is out of reach for the current methods, which rely on the Permutation Invariant Loss (PIT). In this work, we present a permutation invariant training that employs the Hungarian algorithm in order to train with an O(C^3) time complexity, where C is the number of speakers, in comparison to O(C!) of PIT based methods. Furthermore, we present a modified architecture that can handle the increased number of speakers. Our approach separates up to 20 speakers and improves the previous results for large C by a wide margin.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 4

04/05/2019

Recursive speech separation for unknown number of speakers

In this paper we propose a method of single-channel speaker-independent ...
06/22/2021

Multi-accent Speech Separation with One Shot Learning

Speech separation is a problem in the field of speech processing that ha...
10/08/2021

Location-based training for multi-channel talker-independent speaker separation

Permutation-invariant training (PIT) is a dominant approach for addressi...
03/27/2020

Separating Varying Numbers of Sources with Auxiliary Autoencoding Loss

Many recent source separation systems are designed to separate a fixed n...
11/04/2020

Single channel voice separation for unknown number of speakers under reverberant and noisy settings

We present a unified network for voice separation of an unknown number o...
07/30/2021

Graph-PIT: Generalized permutation invariant training for continuous separation of arbitrary numbers of speakers

Automatic transcription of meetings requires handling of overlapped spee...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.