How Far Are We From Robust Voice Conversion: A Survey
2020 · Tzu-Hsien Huang, Jheng-Hao Lin, Chien-Yu Huang, et al.
Abstract
Voice conversion technologies have been greatly improved in recent years with the help of deep learning, but their capabilities of producing natural sounding utterances in different conditions remain unclear. In this paper, we gave a thorough study of the robustness of known VC models. We also modified these models, such as the replacement of speaker embeddings, to further improve their performances. We found that the sampling rate and audio duration greatly influence voice conversion. All the VC models suffer from unseen data, but AdaIN-VC is relatively more robust. Also, the speaker embedding jointly trained is more suitable for voice conversion than those trained on speaker identification.
Authors
(none)
Tags
Stats
Related papers
- An Overview Of Voice Conversion And Its Challenges: From Statistical Modeling To Deep Learning (2020)18.53
- Generative Adversarial Network Based Voice Conversion: Techniques, Challenges, And Recent Advancements (2025)0.00
- Measuring The Effectiveness Of Voice Conversion On Speaker Identification And Automatic Speech Recognition Systems (2019)0.00
- Robustness Of Voice Conversion Techniques Under Mismatched Conditions (2016)0.00
- Toward Degradation-robust Voice Conversion (2021)5.84
- Assem-vc: Realistic Voice Conversion By Assembling Modern Speech Synthesis Techniques (2021)11.64
- Towards Robust Neural Vocoding For Speech Generation: A Survey (2019)0.00
- Voice Conversion Can Improve ASR In Very Low-resource Settings (2021)7.50