Picture for Yuan Wan

Yuan Wan

ByteComposer: a Human-like Melody Composition Method based on Language Model Agent

Add code
Mar 07, 2024
Viaarxiv icon

Semantic Graph Neural Network with Multi-measure Learning for Semi-supervised Classification

Add code
Dec 04, 2022
Viaarxiv icon

Towards High-fidelity Singing Voice Conversion with Acoustic Reference and Contrastive Predictive Coding

Add code
Oct 10, 2021
Figure 1 for Towards High-fidelity Singing Voice Conversion with Acoustic Reference and Contrastive Predictive Coding
Figure 2 for Towards High-fidelity Singing Voice Conversion with Acoustic Reference and Contrastive Predictive Coding
Figure 3 for Towards High-fidelity Singing Voice Conversion with Acoustic Reference and Contrastive Predictive Coding
Figure 4 for Towards High-fidelity Singing Voice Conversion with Acoustic Reference and Contrastive Predictive Coding
Viaarxiv icon

PPG-based singing voice conversion with adversarial representation learning

Add code
Oct 28, 2020
Figure 1 for PPG-based singing voice conversion with adversarial representation learning
Figure 2 for PPG-based singing voice conversion with adversarial representation learning
Figure 3 for PPG-based singing voice conversion with adversarial representation learning
Figure 4 for PPG-based singing voice conversion with adversarial representation learning
Viaarxiv icon

High-resolution Piano Transcription with Pedals by Regressing Onsets and Offsets Times

Add code
Oct 05, 2020
Figure 1 for High-resolution Piano Transcription with Pedals by Regressing Onsets and Offsets Times
Figure 2 for High-resolution Piano Transcription with Pedals by Regressing Onsets and Offsets Times
Figure 3 for High-resolution Piano Transcription with Pedals by Regressing Onsets and Offsets Times
Figure 4 for High-resolution Piano Transcription with Pedals by Regressing Onsets and Offsets Times
Viaarxiv icon