Picture for Xia Liang

Xia Liang

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

Add code
Mar 07, 2024
Viaarxiv icon

ByteCover3: Accurate Cover Song Identification on Short Queries

Add code
Mar 21, 2023
Viaarxiv icon

Attention-based cross-modal fusion for audio-visual voice activity detection in musical video streams

Add code
Jun 21, 2021
Figure 1 for Attention-based cross-modal fusion for audio-visual voice activity detection in musical video streams
Figure 2 for Attention-based cross-modal fusion for audio-visual voice activity detection in musical video streams
Figure 3 for Attention-based cross-modal fusion for audio-visual voice activity detection in musical video streams
Figure 4 for Attention-based cross-modal fusion for audio-visual voice activity detection in musical video streams
Viaarxiv icon

MIDI-Sandwich2: RNN-based Hierarchical Multi-modal Fusion Generation VAE networks for multi-track symbolic music generation

Add code
Sep 08, 2019
Figure 1 for MIDI-Sandwich2: RNN-based Hierarchical Multi-modal Fusion Generation VAE networks for multi-track symbolic music generation
Figure 2 for MIDI-Sandwich2: RNN-based Hierarchical Multi-modal Fusion Generation VAE networks for multi-track symbolic music generation
Figure 3 for MIDI-Sandwich2: RNN-based Hierarchical Multi-modal Fusion Generation VAE networks for multi-track symbolic music generation
Figure 4 for MIDI-Sandwich2: RNN-based Hierarchical Multi-modal Fusion Generation VAE networks for multi-track symbolic music generation
Viaarxiv icon

MIDI-Sandwich: Multi-model Multi-task Hierarchical Conditional VAE-GAN networks for Symbolic Single-track Music Generation

Add code
Jul 04, 2019
Figure 1 for MIDI-Sandwich: Multi-model Multi-task Hierarchical Conditional VAE-GAN networks for Symbolic Single-track Music Generation
Figure 2 for MIDI-Sandwich: Multi-model Multi-task Hierarchical Conditional VAE-GAN networks for Symbolic Single-track Music Generation
Figure 3 for MIDI-Sandwich: Multi-model Multi-task Hierarchical Conditional VAE-GAN networks for Symbolic Single-track Music Generation
Figure 4 for MIDI-Sandwich: Multi-model Multi-task Hierarchical Conditional VAE-GAN networks for Symbolic Single-track Music Generation
Viaarxiv icon