AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

VoiceMixer: Adversarial Voice Style Mixup

Sang-Hoon Lee, Ji-Hoon Kim, Hyunseung Chung, Seong-Whan Lee

NeurIPS 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 15 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add contrastive losses Lpos and Lneg (ablation)VoiceMixer · VCTK zero-shotSimilarity: 42.3% -> 63.7%Improved
add negative contrastive loss Lneg (ablation)VoiceMixer · VCTK zero-shotNaturalness MOS: 3.18 -> 3.72Improved
add adversarial speaker classification Ladvsc (ablation)VoiceMixer · VCTK zero-shotSimilarity: 41.3% -> 63.7%Improved
add adversarial speaker classification Ladvsc (ablation)VoiceMixer · VCTK zero-shotFDSD: 1.217 -> 2.416Hurt
use similarity-based bottleneck instead of fixed-length (tau=16) (ablation)VoiceMixer · VCTK zero-shotNaturalness MOS: 3.35 -> 3.72Improved
use similarity-based bottleneck instead of fixed-length (tau=32) (ablation)VoiceMixer · VCTK zero-shotASV EER: 20.7% -> 18.5%Improved
add GAN training (ablation)VoiceMixer · VCTK zero-shotFDSD: 2.666 -> 2.416Improved
use disentangled content/style discriminator instead of single discriminator (ablation)VoiceMixer · VCTK zero-shotFDSD: 3.502 -> 2.416Improved
add repulsive style loss (ablation)VoiceMixer · VCTK zero-shotSimilarity: 55.0% -> 63.7%Improved
add repulsive style loss (ablation)VoiceMixer · VCTK zero-shotFDSD: 2.173 -> 2.416Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy