Pith. sign in

REVIEW 1 cited by

Remix-cycle-consistent Learning on Adversarially Learned Separator for Accurate and Stable Unsupervised Speech Separation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2203.14080 v1 pith:DE2M37HY submitted 2022-03-26 eess.AS cs.SD

classification eess.AScs.SD
keywords separationlearningspeechlossnetworksadversariallylearnedmixed
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

A new learning algorithm for speech separation networks is designed to explicitly reduce residual noise and artifacts in the separated signal in an unsupervised manner. Generative adversarial networks are known to be effective in constructing separation networks when the ground truth for the observed signal is inaccessible. Still, weak objectives aimed at distribution-to-distribution mapping make the learning unstable and limit their performance. This study introduces the remix-cycle-consistency loss as a more appropriate objective function and uses it to fine-tune adversarially learned source separation models. The remix-cycle-consistency loss is defined as the difference between the mixed speech observed at microphones and the pseudo-mixed speech obtained by alternating the process of separating the mixed sound and remixing its outputs with another combination. The minimization of this loss leads to an explicit reduction in the distortions in the output of the separation network. Experimental comparisons with multichannel speech separation demonstrated that the proposed method achieved high separation accuracy and learning stability comparable to supervised learning.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Developing an Effective Training Dataset to Enhance the Performance of AI-based Speaker Separation Systems

    cs.SD 2024-11 conditional novelty 4.0 of 10

    A playback-and-record method creates a realistic two-speaker training set that yields up to 1.65 dB SI-SDR improvement over synthetic training.

Pith tools