SeungHeon Doh's repositories
lp-music-caps
LP-MusicCaps: LLM-Based Pseudo Music Captioning [ISMIR23]
music-text-representation
Toward Universal Text-to-Music-Retrieval (TTMR) [ICASSP23]
msd-subsets
million song dataset split for extended clean tag & artist-level stratified
music_caps_dl
Unofficial download repository for MusicCaps
msu-benchmark
music semantic understanding evaluation benchmark
musical-word-embedding
Musical Word Embedding for Music Tagging and Retrieval [IEEE TASLP]
speech-to-music
Textless Speech-to-Music Retrieval Using Emotion Similarity [ICASSP23]
music-text-representation-pp
Enriching Music Descriptions with a Finetuned-LLM and Metadata for Text-to-Music Retrieval (TTMR++) [ICASSP24]
music-data-leakage
data leakage problem between large music datasets
gtzan-bind
bind annotations in gtzan dataset
music-captioning-eval
compare captioning evaluation framework (Huggingface evaluate vs Coco-eval)
musical_word_embedding_demo
https://seungheondoh.github.io/musical_word_embedding_demo/
olga-msd
mappings between MSD tracks and OLGA artists
speech-to-music-demo
https://seungheondoh.github.io/speech-to-music-demo/