Singing Voice Conversion With Disentangled Representations Of Singer And Vocal Technique Using Variational Autoencoders

Abstract

We propose a flexible framework that deals with both singer conversion and singers vocal technique conversion. The proposed model is trained on non-parallel corpora, accommodates many-to-many conversion, and leverages recent advances of variational autoencoders. It employs separate encoders to learn disentangled latent representations of singer identity and vocal technique separately, with a joint decoder for reconstruction. Conversion is carried out by simple vector arithmetic in the learned latent spaces. Both a quantitative analysis as well as a visualization of the converted spectrograms show that our model is able to disentangle singer identity and vocal technique and successfully perform conversion of these attributes. To the best of our knowledge, this is the first work to jointly tackle conversion of singer identity and vocal technique based on a deep learning approach.

Stats

• citations28
• S2 citations—
• github stars0
• HF likes0
• heat score10.97
• arxiv keyluo2019singing

Related papers

• Unsupervised Singing Voice Conversion (2019)11.19
• Many-to-many Voice Conversion Based Feature Disentanglement Using Variational Autoencoder (2021)7.81
• Non-parallel Sequence-to-sequence Voice Conversion With Disentangled Linguistic And Speaker Representations (2019)14.02
• Hierarchical Disentangled Representation Learning For Singing Voice Conversion (2021)6.34
• Learning In Your Voice: Non-parallel Voice Conversion Based On Speaker Consistency Loss (2020)0.00
• Singing Voice Conversion With Non-parallel Data (2019)9.59
• Ppg-based Singing Voice Conversion With Adversarial Representation Learning (2020)9.76
• A Comparative Analysis Of Latent Regressor Losses For Singing Voice Conversion (2023)0.00