Voice Conversion
151 papers with code • 2 benchmarks • 5 datasets
Voice Conversion is a technology that modifies the speech of a source speaker and makes their speech sound like that of another target speaker without changing the linguistic information.
Benchmarks
These leaderboards are used to track progress in Voice Conversion
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
Libraries
Use these libraries to find Voice Conversion models and implementations
LibriSpeech
ESD
VESUS
Latest papers
Low-latency Real-time Voice Conversion on CPU
koeai/llvc
•
•
To our knowledge LLVC achieves both the lowest resource usage as well as the lowest latency of any open-source voice conversion model.
Non-Parallel Training Approach for Emotional Voice Conversion Using CycleGAN
MohamedElsayed-22/non-parallel-training-for-emotion-conversion-of-arabic-speech-using-cycleGAN-and-WORLD-Vocoder
•
•
20th International Conference on Informatics in Control, Automation and Robotics 2023
The focus of this research is proposing a nonparallel emotional voice conversion for Egyptian Arabic speech.
BiSinger: Bilingual Singing Voice Synthesis
We fuse monolingual singing datasets with open-source singing voice conversion techniques to generate bilingual singing voices while also exploring the potential use of bilingual speech data.
HM-Conformer: A Conformer-based audio deepfake detection system with hierarchical pooling and multi-level classification token aggregation methods
Audio deepfake detection (ADD) is the task of detecting spoofing attacks generated by text-to-speech or voice conversion systems.
Emo-StarGAN: A Semi-Supervised Any-to-Many Non-Parallel Emotion-Preserving Voice Conversion
Speech anonymisation prevents misuse of spoken data by removing any personal identifier while preserving at least linguistic content.
StarGAN-VC++: Towards Emotion Preserving Voice Conversion Using Deep Embeddings
arnabdas8901/StarGAN-VC_PlusPlus
•
•
In this paper, we show that StarGANv2-VC fails to disentangle the speaker and emotion representations, pertinent to preserve emotion.
Evaluating Methods for Ground-Truth-Free Foreign Accent Conversion
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 and control the speaker identity.
FSD: An Initial Chinese Dataset for Fake Song Detection
In this paper, we initially construct a Chinese Fake Song Detection (FSD) dataset to investigate the field of song deepfake detection.
Phoneme Hallucinator: One-shot Voice Conversion via Set Expansion
PhonemeHallucinator/Phoneme_Hallucinator
•
•
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
voice-privacy-challenge/voice-privacy-challenge-2024
•
•
The growing use of voice user interfaces has led to a surge in the collection and storage of speech data.
