How Far Are We from Robust Voice Conversion: A Survey

By Tzu-hsien Huang, Jheng-hao Lin, Chien-yu Huang, Hung-yi Lee. 2020

34 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

UniAudio: An Audio Foundation Model Toward Universal Audio Generation (2023, background): “Prior works on audio generation tasks are commonly task-specific: their designs heavily leverage domain knowledge and their usage is restricted to fixed setups (Tan et al., 2021; Luo & Mesgarani, 2019; Zmolikova et al., 2023; Huang et al., 2021b; Cho et al., 2021).”
Deepfakes generation and detection: state-of-the-art, open challenges, countermeasures, and way forward (2021, background): “Due to recent advances in TTS [52, 193] and VC [227] techniques, audio deepfakes have become an increased threat”