SAGE: Semantic Audio Generative Encoder
cs.SD, cs.LG, eess.AS
Submitted: 2026-09-26
Updated: 2026-09-26
Code: https://github.com/francescobrigante/SAGE
Project page: https://sage-music.pages.dev
Terminology
Sources
- Stable Audio 3
- Distilling the Knowledge in a Neural Network
- The Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation
- UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
- SAME: A Semantically-Aligned Music Autoencoder
- GLU Variants Improve Transformer
Related papers
- Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
- Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
- AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
- SoundWeaver: Compositional Warm-Starting for Text-to-Audio Diffusion Serving
- WASIL: In-the-Wild Arabic Spoken Interactions with LLMs
- Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment