Voice Conversion

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

3 leaderboard tables shown for this task, 3 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

8 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 175 papers with code (520 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networks
  6 Jun 2018 14 repositories listed Syntology ran 2 of 4 samples · 2 unverified · 4 pointer-only (licence)
  This paper proposes a method that allows non-parallel many-to-many voice conversion (VC) by using a variant of a generative adversarial network (GAN) called StarGAN.
• AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss
  14 May 2019 11 repositories listed
  On the other hand, CVAE training is simple but does not come with the distribution-matching property of a GAN.
• One-shot Voice Conversion by Separating Speaker and Content Representations with Instance Normalization
  10 Apr 2019 11 repositories listed Syntology ran 0 of 9 samples · 9 unverified
  Recently, voice conversion (VC) without parallel data has been successfully adapted to multi-target scenario in which a single model is trained to convert the input voice to many different speakers.
• Parallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networks
  30 Nov 2017 9 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  A subjective evaluation showed that the quality of the converted speech was comparable to that obtained with a Gaussian mixture model-based method under advantageous conditions with parallel and twice the amount of data.
• Utilizing Self-supervised Representations for MOS Prediction
  7 Apr 2021 7 repositories listed Syntology ran 0 of 1 samples · 1 unverified
  In this paper, we use self-supervised pre-trained models for MOS prediction.
• MOSNet: Deep Learning based Objective Assessment for Voice Conversion
  17 Apr 2019 7 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  In this paper, we propose deep learning-based assessment models to predict human ratings of converted speech.
• SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing
  14 Oct 2021 6 repositories listed Syntology ran 2 of 3 samples · 1 unverified · 3 pointer-only (licence)
  Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural language processing models, we propose a unified-modal SpeechT5 framework that explores the encoder-decoder pre-training for…
• Defense for Black-box Attacks on Anti-spoofing Models by Self-Supervised Learning
  5 Jun 2020 6 repositories listed
  To explore this issue, we proposed to employ Mockingjay, a self-supervised learning based model, to protect anti-spoofing models against adversarial attacks in the black-box scenario.
• Unsupervised Speech Decomposition via Triple Information Bottleneck
  23 Apr 2020 6 repositories listed Syntology ran 0 of 12 samples · 12 unverified
  Speech information can be roughly decomposed into four components: language content, timbre, pitch, and rhythm.
• CycleGAN-VC2: Improved CycleGAN-based Non-parallel Voice Conversion
  9 Apr 2019 6 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  Non-parallel voice conversion (VC) is a technique for learning the mapping from source to target speech without relying on parallel data.
• Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks
  23 Sep 2017 5 repositories listed
  In the proposed framework incorporating the GANs, the discriminator is trained to distinguish natural and generated speech parameters, while the acoustic models are trained to minimize the weighted sum of the…
• Voice Conversion from Non-parallel Corpora Using Variational Auto-encoder
  13 Oct 2016 5 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  We propose a flexible framework for spectral conversion (SC) that facilitates training with unaligned corpora.
• Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme
  28 Sep 2021 4 repositories listed Syntology ran 6 of 9 samples · 3 unverified · 9 pointer-only (licence)
  Voice conversion is a common speech synthesis task which can be solved in different ways depending on a particular real-world scenario.
• S2VC: A Framework for Any-to-Any Voice Conversion with Self-Supervised Pretrained Representations
  7 Apr 2021 4 repositories listed
  AUTOVC used dvector to extract speaker information, and self-supervised learning (SSL) features like wav2vec 2.
• AraBERT: Transformer-based Model for Arabic Language Understanding
  28 Feb 2020 4 repositories listed
  Recently, with the surge of transformers based models, language-specific BERT based models have proven to be very efficient at language understanding, provided they are pre-trained on a very large corpus.
• YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone
  4 Dec 2021 3 repositories listed
  YourTTS brings the power of a multilingual approach to the task of zero-shot multi-speaker TTS.
• MaskCycleGAN-VC: Learning Non-parallel Voice Conversion with Filling in Frames
  25 Feb 2021 3 repositories listed
  With FIF, we apply a temporal mask to the input mel-spectrogram and encourage the converter to fill in missing frames based on surrounding frames.
• One-class learning towards generalized voice spoofing detection
  27 Oct 2020 3 repositories listed Syntology ran 0 of 10 samples · 10 unverified
  Human voices can be used to authenticate the identity of the speaker, but the automatic speaker verification (ASV) systems are vulnerable to voice spoofing attacks, such as impersonation, replay, text-to-speech, and…
• The Sequence-to-Sequence Baseline for the Voice Conversion Challenge 2020: Cascading ASR and TTS
  6 Oct 2020 3 repositories listed
  This paper presents the sequence-to-sequence (seq2seq) baseline system for the voice conversion challenge (VCC) 2020.
• Cotatron: Transcription-Guided Speech Encoder for Any-to-Many Voice Conversion without Parallel Data
  7 May 2020 3 repositories listed
  We propose Cotatron, a transcription-guided speech encoder for speaker-independent linguistic representation.
• StarGAN-VC2: Rethinking Conditional Methods for StarGAN-Based Voice Conversion
  29 Jul 2019 3 repositories listed Syntology ran 2 of 3 samples · 1 unverified · 3 pointer-only (licence)
  To bridge this gap, we rethink conditional methods of StarGAN-VC, which are key components for achieving non-parallel multi-domain VC in a single model, and propose an improved variant called StarGAN-VC2.
• Blow: a single-scale hyperconditioned flow for non-parallel raw-audio voice conversion
  3 Jun 2019 3 repositories listed Syntology ran 1 of 5 samples · 4 unverified
  End-to-end models for raw audio generation are a challenge, specially if they have to work with non-parallel data, which is a desirable setup in many situations.
• Multi-target Voice Conversion without Parallel Data by Adversarially Learning Disentangled Audio Representations
  9 Apr 2018 3 repositories listed Syntology ran 0 of 2 samples · 2 unverified · 2 pointer-only (licence)
  The decoder then takes the speaker-independent latent representation and the target speaker embedding as the input to generate the voice of the target speaker with the linguistic content of the source utterance.
• Audio Deepfake Detection with Self-Supervised XLS-R and SLS Classifier
  28 Oct 2024 2 repositories listed
  To enhance the sensitivity of deepfake audio features, we propose a deepfake audio detection model that incorporates an SLS (Sensitive Layer Selection) module.
• HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech Synthesis
  21 Nov 2023 2 repositories listed Syntology ran 2 of 3 samples · 1 unverified · 1 pointer-only (licence)
  Furthermore, we significantly improve the naturalness and speaker similarity of synthetic speech even in zero-shot speech synthesis scenarios.
• Evaluating Methods for Ground-Truth-Free Foreign Accent Conversion
  5 Sep 2023 2 repositories listed
  In this work, we evaluate three recently proposed methods for ground-truth-free FAC, where all of them aim to harness the power of sequence-to-sequence (seq2seq) and non-parallel VC models to properly convert the accent…
• Phoneme Hallucinator: One-shot Voice Conversion via Set Expansion
  11 Aug 2023 2 repositories listed
  Objective and subjective evaluations show that \textit{Phoneme Hallucinator} outperforms existing VC methods for both intelligibility and speaker similarity.
• Anonymizing Speech: Evaluating and Designing Speaker Anonymization Techniques
  5 Aug 2023 2 repositories listed
  The growing use of voice user interfaces has led to a surge in the collection and storage of speech data.
• SpeechLMScore: Evaluating speech generation using speech language model
  8 Dec 2022 2 repositories listed Syntology ran 1 of 9 samples · 8 unverified
  While human evaluation is the most reliable metric for evaluating speech generation systems, it is generally costly and time-consuming.
• iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform
  4 Mar 2022 2 repositories listed Syntology ran 8 of 11 samples · 3 unverified
  In recent text-to-speech synthesis and voice conversion systems, a mel-spectrogram is commonly applied as an intermediate representation, and the necessity for a mel-spectrogram vocoder is increasing.

Syntology lines on 17 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.