ICASSP2025 音楽系論文一人読み会
#icassp2025
音楽系論文を読み散らかす。不定期更新
読みたいリスト
Aligned Contrastive Learning for Text-to-Music Retrieval
BeatKAN An Efficient and Drum-Attuned Beat Tracking Method Using Kolmogorov-Arnold Networks
Bootstrapping Language-Audio Pre-training for Music Captioning
DOSE Drum One-Shot Extraction from Music Mixture
Editing Music with Melody and Text Using ControlNet for Diffusion Transformer
EEG-Music Emotion Recognition Challenge Overview
Exploring Acoustic Similarity in Emotional Speech and Music via Self-Supervised Representations
FUTGA-MIR Enhancing Fine-grained and Temporally-aware Music Understanding with Music Information Retrieval
Investigating the Sensitivity of Pre-trained Audio Embeddings to Common Effects
KCE-Unet A novel music denoising method with KANConv ECA Unet
Keep what you need extracting efficient subnetworks from large audio representation models
Learning Source Disentanglement in Neural Audio Codec
Leave-One-EquiVariant Alleviating Invariance-Related Information Loss in Contrastive Music Representations
Melody Structure Transfer Network Generating Music with Separable Self-Attention
No Data Required Zero-Shot Domain Adaptation for Automatic Music Transcription
Open-Amp Synthetic Data Framework for Audio Effect Foundation Models
Simultaneous Music Separation and Generation Using Multi-Track Latent Diffusion Models
Singing Voice Conversion with Accompaniment Using Self-Supervised Representation-Based Melody Features
S-KEY Self-supervised Learning of Major and Minor Keys from Audio
TokenSynth A Token-based Neural Synthesizer for Instrument Cloning and Text-to-Instrument
Ultra Lightweight Singing Melody Extraction via Combination of Convolution and MLP
Unsupervised Domain Adaptation for Music Transcription Exploiting Cross-Version Consistency
A Hierarchical Taxonomy For Deep State Space Models
A Mamba-based Network for Semi-supervised Singing Melody Extraction Using Confidence Binary Regularization
A Singing Melody Extraction Network Via Self-Distillation and Multi-Level Supervision