Freevc: Towards High-Quality Text-Free One-Shot Voice Conversion
The DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index.
Abstract
Voice conversion (VC) can be achieved by first extracting source content information and target speaker information, and then reconstructing waveform with these information. However, current approaches normally either extract dirty content information with speaker information leaked in, or demand a large amount of annotated data for training. Besides, the quality of reconstructed waveform can be degraded by the mismatch between conversion model and vocoder. In this paper, we adopt the end-to-end framework of VITS for high-quality waveform reconstruction, and propose strategies for clean content information extraction without text annotation. We disentangle content information by imposing an information bottleneck to WavLM features, and propose the spectrogram-resize based data augmentation to improve the purity of extracted content information. Experimental results show that the proposed method outperforms the latest VC models trained with annotated data and has greater robustness.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Recent research [59,60,61,62,63] in VC technologies has addressed long-standing challenges such as data scarcity, cross-lingual conversion, and real-time processing.”
From Audio Deepfake Detection: What Has Been Achieved and What Lies Ahead (2025) · cites this paper as [62]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Unsupervised Cross-lingual Representation Learning at Scale
Conneau, A., Khandelwal, K., Goyal, N., Chaudhary, V., Wenzek, G., Guzmán, F., Grave, E., Ott, M., Zettlemoyer, L., & Stoyanov, V. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.747 · Cited by 5,637
“Least squares generative adversarial networks,”
Mao, X., Li, Q., Xie, H., Lau, R. Y. K., Wang, Z., & Smolley, S. P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.304 · Cited by 5,437
Pearson Correlation Coefficient
Benesty, J., Chen, J., Huang, Y., & Cohen, I. (2009) · Springer Topics in Signal Processing · doi:10.1007/978-3-642-00296-0_5 · Cited by 3,059
Density estimation using Real NVP
Dinh, L., Sohl-Dickstein, J., & Bengio, S. (2016) · arXiv · Cited by 2,067 · cited 1×
“Following VITS, it is composed of multiple affine coupling layers [19] and is made to be volume-preserving with the Jacobian determinant | det ∂z ′ ∂z | of 1.”
MethodAutoencoding beyond pixels using a learned similarity metric
Larsen, A., Sønderby, S. K., Larochelle, H., & Winther, O. (2016) · Research at the University of Copenhagen (University of Copenhagen) · Cited by 1,990
WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
Chen, S., Wang, C., Chen, Z., Wu, Y., Liu, S., Chen, Z., Li, J., Kanda, N., Yoshioka, T., Xiao, X., et al. (2022) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2022.3188113 · Cited by 1,926 · cited 7×
“We use WavLM [17] to extract SSL features from waveform, and introduce a bottleneck extractor to extract content information from SSL features.”
MethodInfluentialSelf-citationLibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech
Zen, H., Dang, V., Clark, R., Zhang, Y., Weiss, R. J., Jia, Y., Chen, Z., & Wu, Y. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-2441 · Cited by 752
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
Kong, J., Kim, J., & Bae, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.05646 · Cited by 722 · cited 1×
“And a HiFi-GAN v1 vocoder [26] is used to transform the modified mel-spectrogram into waveform.”
MethodStyle Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
Wang, Y., Stanton, D., Zhang, Y., Skerry-Ryan, R., Battenberg, E., Shor, J., Xiao, Y., Ren, F., Ye, J., & Saurous, R. A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.09017 · Cited by 497
CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR Voice Cloning Toolkit (version 0.92)
Yamagishi, J., Veaux, C., & MacDonald, K. (2019) · University of Edinburgh. The Centre for Speech Technology Research (CSTR) · doi:10.7488/ds/2645 · Cited by 356 · cited 1×
“We conduct experiments on VCTK [24] and LibriTTS [25].”
Method
Cited by
MLAAD: The Multi-Language Audio Anti-Spoofing Dataset
Müller, N. M., Kawa, P., Choong, W. H., Casanova, E., Gölge, E., Müller, T., Syga, P., Sperl, P., & Böttinger, K. (2024) · 2024 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650962 · Cited by 73
Audio Deepfake Detection: What Has Been Achieved and What Lies Ahead
Zhang, B., Cui, H., Nguyen, V., & Whitty, M. (2025) · Sensors · doi:10.3390/s25071989 · Cited by 72
Deepfakes as a threat to a speaker and facial recognition: An overview of tools and attack vectors
Firc, A., Malinka, K., & Hanáček, P. (2023) · Heliyon · doi:10.1016/j.heliyon.2023.e15090 · Cited by 78
Video and Audio Deepfake Datasets and Open Issues in Deepfake Technology: Being Ahead of the Curve
Akhtar, Z., Pendyala, T. L., & Athmakuri, V. S. (2024) · Forensic Sciences · doi:10.3390/forensicsci4030021 · Cited by 60
Inie, N., Falk, J., & Selvan, R. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714227 · Cited by 41
Metadata
- Authors
- Li, J., Tu, W., & Xiao, L.
- Affiliations
- Wuhan University (CN)
- Wuhan University,National Engineering Research Center for Multimedia Software, School of Computer Science,Wuhan,China,430072
- Venue
- ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2023-06-04
- Pages
- 1-5
- ISSN
- 1520-6149 (ISSN-L)
- OpenAlex
- W4372260053
- Cited by
- 129
- References
- 31
- Citations by year
- 2026: 24 · 2025: 62 · 2024: 36 · 2023: 7
- FWCI
- 22.74
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Acoustics Speech and Signal Processing (publishedVersion)
- Funders
- Nature
- Fundamental Research Funds for the Central Universities
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Health Sciences › Health Professions › Speech and Hearing › Voice and Speech Disorders
- Keywords
- voice conversion, VITS, WavLM, information bottleneck
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Freevc: Towards High-Quality Text-Free One-Shot Voice Conversion. https://app.cochat.ai/papers/10.1109/icassp49357.2023.10095191
- The paper
- Li, J., Tu, W., & Xiao, L. (2023). Freevc: Towards High-Quality Text-Free One-Shot Voice Conversion. ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp49357.2023.10095191
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.