mlsanityData to 7 Oct 2026

SpeechSplit 2.0: Unsupervised speech disentanglement for voice conversion Without tuning autoencoder Bottlenecks

arXiv 2203.14156 ↗First posted 26 Mar 2022eess.AS cs.AI cs.SDcited by 27

Not on the map. Why?

Abstract (arXiv)

SpeechSplit can perform aspect-specific voice conversion by disentangling speech into content, rhythm, pitch, and timbre using multiple autoencoders in an unsupervised manner. However, SpeechSplit requires careful tuning of the autoencoder bottlenecks, which can be time-consuming and less robust. This paper proposes SpeechSplit 2.0, which constrains the information flow of the speech component to be disentangled on the autoencoder input using efficient signal processing methods instead of bottleneck tuning. Evaluation results show that SpeechSplit 2.0 achieves comparable performance to SpeechSplit in speech disentanglement and superior robustness to the bottleneck size variations. Our code is available at https://github.com/biggytruck/SpeechSplit2.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 12 of its 20 references that are in the map. First posted on arXiv 26 Mar 2022.

Builds on

12 of 20 references.

References · 12

  1. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  2. 2019AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Losscited by 189
  3. 2020Unsupervised Speech Decomposition via Triple Information Bottleneckcited by 87
  4. 2016Voice Conversion from Non-parallel Corpora Using Variational Auto-encodercited by 45
  5. 2019StarGAN-VC2: Rethinking Conditional Methods for StarGAN-Based Voice Conversioncited by 37
  6. 2020F0-consistent many-to-many non-parallel voice conversion via conditional autoencodercited by 35
  7. 2022Investigation of Data Augmentation Techniques for Disordered Speech Recognitioncited by 27
  8. 2018Multi-target Voice Conversion without Parallel Data by Adversarially Learning Disentangled Audio Representationscited by 25
  9. 2020VAW-GAN for Disentanglement and Recomposition of Emotional Elements in Speechcited by 18
  10. 2020Can Speaker Augmentation Improve Multi-Speaker End-to-End TTS?cited by 9
  11. 2018Unsupervised Adaptation with Interpretable Disentangled Representations for Distant Conversational Speech Recognitioncited by 7
  12. 2021Protecting gender and identity with disentangled speech representationscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 4; 2024: 10; 2025: 5; 2026: 3.

27 papers.

Sort:

By area:

  1. 2022FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversioncited by 79
  2. 2023SEF-VC: Speaker Embedding Free Zero-Shot Voice Conversion with Cross Attentioncited by 19
  3. 2022Speech Representation Disentanglement with Adversarial Mutual Information Learning for One-shot Voice Conversioncited by 14
  4. 2023An Efficient Temporary Deepfake Location Approach Based Embeddings for Partially Spoofed Audio Detectioncited by 10
  5. 2024End-to-end streaming model for low-latency speech anonymizationcited by 9
  6. 2022Disentangling Prosody Representations with Unsupervised Speech Reconstructioncited by 8
  7. 2024LSCodec: Low-Bitrate and Speaker-Decoupled Discrete Speech Codeccited by 7
  8. 2024vec2wav 2.0: Advancing Voice Conversion via Discrete Token Vocoderscited by 6
  9. 2024Generalized Source Tracing: Detecting Novel Audio Deepfake Algorithm with Real Emphasis and Fake Dispersion Strategycited by 5
  10. 2024Imperceptible Rhythm Backdoor Attacks: Exploring Rhythm Transformation for Embedding Undetectable Vulnerabilities on Speech Recognitioncited by 5
  11. 2025Discl-VC: Disentangled Discrete Tokens and In-Context Learning for Controllable Zero-Shot Voice Conversioncited by 5
  12. 2026TVTSyn: Content-Synchronous Time-Varying Timbre for Streaming Voice Conversion and Anonymizationcited by 4
15 more
  1. 2022A unified one-shot prosody and speaker conversion system with self-supervised discrete speech unitscited by 3
  2. 2024PSCodec: A Series of High-Fidelity Low-bitrate Neural Speech Codecs Leveraging Prompt Encoderscited by 3
  3. 2024Representation Purification for End-to-End Speech Translationcited by 3
  4. 2025ZSVC: Zero-shot Style Voice Conversion with Disentangled Latent Diffusion Models and Adversarial Trainingcited by 3
  5. 2022Improved disentangled speech representations using contrastive learning in factorized hierarchical variational autoencodercited by 2
  6. 2023AlignSTS: Speech-to-Singing Conversion via Cross-Modal Alignmentcited by 2
  7. 2024Towards Evaluating the Robustness of Automatic Speech Recognition Systems via Audio Style Transfercited by 2
  8. 2025Whispering Under the Eaves: Protecting User Privacy Against Commercial and LLM-powered Automatic Speech Recognition Systemscited by 2
  9. 2025Voice Conversion for Lombard Speaking Style with Implicit and Explicit Acoustic Feature Conditioningcited by 1
  10. 2025NE-PADD: Leveraging Named Entity Knowledge for Robust Partial Audio Deepfake Detection via Attention Aggregationcited by 1
  11. 2023Automatic Speech Disentanglement for Voice Conversion using Rank Module and Speech Augmentationcited by 0
  12. 2024An Unsupervised Domain Adaptation Method for Locating Manipulated Region in partially fake Audiocited by 0
  13. 2024Pureformer-VC: Non-parallel One-Shot Voice Conversion with Pure Transformer Blocks and Triplet Discriminative Trainingcited by 0
  14. 2026StyleStream: Real-Time Zero-Shot Voice Style Conversioncited by 0
  15. 2026Do speech foundation models really learn words?cited by 0