- Audio Spectrogram Transformer(AST) |
- Listen, Think, and Understand(LTU) |
- Music Emotion Maps in Arousal-Valence Space
- MERT: Acoustic Music Understanding Model with Large-Scale Self-Supervised Training |
- Audio Signal Mapping into Spectrogram-Based Images for Deep Learning Applications
- Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning |
Team Leader- Listen, Think, and Understand
Paper Review - Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning
Paper Review - MU-LLaMA
Fine-tuning & Evaluation
- LLark: A Multimodal Instruction-Following Language Model for Music
Paper Review - LLaMA-7B-instruct
Pretraining - Database
Data Preprocessing - GPT API
Prompting
- LLark: A Multimodal Instruction-Following Language Model for Music
Paper Review - MU-LLaMA
Environment Setting(Attempt for upgrading LLaMA2 to LLaMA3)
- MERT: Acoustic Music Understanding Model with Large-Scale Self-Supervised Training
Paper Review Database ImplementationSever Develop
- Listen, Think, and Understand
Paper Review Database ImplementationSever Develop
- MERT: Acoustic Music Understanding Model with Large-Scale Self-Supervised Training
Paper Review Client Develop