Pith. sign in

REVIEW 4 cited by

StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2107.10394 v2 pith:LKE3LTIJ submitted 2021-07-21 cs.SD cs.LGeess.AS

StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion

Yinghao Aaron Li , Ali Zare , Nima Mesgarani This is my paper
classification cs.SD cs.LGeess.AS
keywords conversionvoicemodelnon-parallelspeechadversarialframeworkloss
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We present an unsupervised non-parallel many-to-many voice conversion (VC) method using a generative adversarial network (GAN) called StarGAN v2. Using a combination of adversarial source classifier loss and perceptual loss, our model significantly outperforms previous VC models. Although our model is trained only with 20 English speakers, it generalizes to a variety of voice conversion tasks, such as any-to-many, cross-lingual, and singing conversion. Using a style encoder, our framework can also convert plain reading speech into stylistic speech, such as emotional and falsetto speech. Subjective and objective evaluation experiments on a non-parallel many-to-many voice conversion task revealed that our model produces natural sounding voices, close to the sound quality of state-of-the-art text-to-speech (TTS) based voice conversion methods without the need for text labels. Moreover, our model is completely convolutional and with a faster-than-real-time vocoder such as Parallel WaveGAN can perform real-time voice conversion.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

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

  1. What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection

    cs.SD 2026-07 conditional novelty 6.0

    Underrepresented gender in training suffers higher deepfake-detection error; WavLM gaps stay large under balance, and all post-hoc calibrations leave the EER gap fixed at 1.317 pp.

  2. ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks

    eess.AS 2026-04 unverdicted novelty 6.0

    ProSDD learns speaker-conditioned prosodic variation from real speech via supervised masked prediction and jointly optimizes it with spoof detection, cutting EER substantially on ASVspoof 2024 and emotional datasets.

  3. AT-ADD: All-Type Audio Deepfake Detection Challenge Evaluation Plan

    cs.SD 2026-04 unverdicted novelty 3.0

    AT-ADD introduces standardized tracks and datasets for evaluating audio deepfake detectors on speech under real-world conditions and on diverse unknown audio types to promote generalization beyond speech-centric methods.

  4. Intelligent Agents with Emotional Intelligence: Current Trends, Challenges, and Future Prospects

    cs.HC 2025-10 unverdicted novelty 2.0

    A holistic survey of affective computing for intelligent agents covering emotion understanding via multimodal data, affective cognition, emotional expression synthesis, key challenges, and future directions emphasizin...