mlsanityData to 7 Oct 2026

AGAIN-VC: A One-shot Voice Conversion using Activation Guidance and Adaptive Instance Normalization

arXiv 2011.00316 ↗First posted 31 Oct 2020eess.AS cs.SDcited by 44

Not on the map. Why?

Abstract (arXiv)

Recently, voice conversion (VC) has been widely studied. Many VC systems use disentangle-based learning techniques to separate the speaker and the linguistic content information from a speech signal. Subsequently, they convert the voice by changing the speaker information to that of the target speaker. To prevent the speaker information from leaking into the content embeddings, previous works either reduce the dimension or quantize the content embedding as a strong information bottleneck. These mechanisms somehow hurt the synthesis quality. In this work, we propose AGAIN-VC, an innovative VC system using Activation Guidance and Adaptive Instance Normalization. AGAIN-VC is an auto-encoder-based model, comprising of a single encoder and a decoder. With a proper activation as an information bottleneck on content embeddings, the trade-off between the synthesis quality and the speaker similarity of the converted speech is improved drastically. This one-shot VC system obtains the best performance regardless of the subjective or objective evaluations.

Key facts. Cited by 44 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 7; 2023: 9; 2024: 9; 2025: 4; 2026: 6.

44 papers.

Sort:

By area:

  1. 2021Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Schemecited by 99
  2. 2022FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversioncited by 79
  3. 2022ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakerscited by 73
  4. 2021VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversioncited by 63
  5. 2022StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech Synthesiscited by 32
  6. 2021Catch-A-Waveform: Learning to Generate Audio from a Single Short Examplecited by 15
  7. 2022Speaking Style Conversion in the Waveform Domain Using Discrete Self-Supervised Unitscited by 15
  8. 2021Adversarially learning disentangled speech representations for robust multi-factor voice conversioncited by 14
  9. 2023An Efficient Temporary Deepfake Location Approach Based Embeddings for Partially Spoofed Audio Detectioncited by 10
  10. 2024End-to-end streaming model for low-latency speech anonymizationcited by 9
  11. 2021Training Robust Zero-Shot Voice Conversion Models with Self-supervised Featurescited by 7
  12. 2024Improving child speech recognition with augmented child-like speechcited by 7
32 more
  1. 2024VQ-CTAP: Cross-Modal Fine-Grained Sequence Representation Learning for Speech Processingcited by 7
  2. 2024FastVoiceGrad: One-step Diffusion-Based Voice Conversion with Adversarial Conditional Diffusion Distillationcited by 7
  3. 2021Zero-shot Voice Conversion via Self-supervised Prosody Representation Learningcited by 6
  4. 2022VisageSynTalk: Unseen Speaker Video-to-Speech Synthesis via Speech-Visage Feature Selectioncited by 6
  5. 2021SIG-VC: A Speaker Information Guided Zero-shot Voice Conversion System for Both Human Beings and Machinescited by 5
  6. 2022Robust One-Shot Singing Voice Conversioncited by 5
  7. 2023SelfVC: Voice Conversion With Iterative Refinement using Self Transformationscited by 5
  8. 2023Self-Supervised Disentangled Representation Learning for Robust Target Speech Extractioncited by 5
  9. 2021NoiseVC: Towards High Quality Zero-Shot Voice Conversioncited by 4
  10. 2023Catch You and I Can: Revealing Source Voiceprint Against Voice Conversioncited by 4
  11. 2025ReFlow-VC: Zero-shot Voice Conversion Based on Rectified Flow and Speaker Feature Optimizationcited by 4
  12. 2026TVTSyn: Content-Synchronous Time-Varying Timbre for Streaming Voice Conversion and Anonymizationcited by 4
  13. 2023SLMGAN: Exploiting Speech Language Model Representations for Unsupervised Zero-Shot Voice Conversion in GANscited by 3
  14. 2023Low-latency Real-time Voice Conversion on CPUcited by 3
  15. 2024PSCodec: A Series of High-Fidelity Low-bitrate Neural Speech Codecs Leveraging Prompt Encoderscited by 3
  16. 2024Disentangling segmental and prosodic factors to non-native speech comprehensibilitycited by 3
  17. 2025FasterVoiceGrad: Faster One-step Diffusion-Based Voice Conversion with Adversarial Diffusion Conversion Distillationcited by 2
  18. 2025LatentVoiceGrad: Nonparallel Voice Conversion with Latent Diffusion/Flow-Matching Modelscited by 2
  19. 2021OCTOPUS: Overcoming Performance andPrivatization Bottlenecks in Distributed Learningcited by 1
  20. 2023Cross-modal Face- and Voice-style Transfercited by 1
  21. 2023Iteratively Improving Speech Recognition and Voice Conversioncited by 1
  22. 2024Converting Anyone's Voice: End-to-End Expressive Voice Conversion with a Conditional Diffusion Modelcited by 1
  23. 2024Discrete Unit based Masking for Improving Disentanglement in Voice Conversioncited by 1
  24. 2025NE-PADD: Leveraging Named Entity Knowledge for Robust Partial Audio Deepfake Detection via Attention Aggregationcited by 1
  25. 2026MeanVoiceFlow: One-step Nonparallel Voice Conversion with Mean Flowscited by 1
  26. 2022MetaSpeech: Speech Effects Switch Along with Environment for Metaversecited by 0
  27. 2023AutoCycle-VC: Towards Bottleneck-Independent Zero-Shot Cross-Lingual Voice Conversioncited by 0
  28. 2024Who is Authentic Speakercited by 0
  29. 2026Koopman Regularized Deep Speech Disentanglement for Speaker Verificationcited by 0
  30. 2026DAST: A Dual-Stream Voice Anonymization Attacker with Staged Trainingcited by 0
  31. 2026From A to B to A: Palindromic Zero-Shot Voice Conversion with Non-Parallel Datacited by 0
  32. 2026MeanVoiceFlow2: Joint Optimization of Mean Flow and Content Encoder for Fast One-Step Zero-Shot Voice Conversioncited by 0