MuLan: A Joint Audio-Text Embedding Model for Music Retrieval

Home

Discover

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and Machine Learning and more.Subscribe

CC BY

Source arXiv

Sound

Audio and Speech Processing

Computation and Language

Stats Machine Learning

MuLan: A Joint Audio-Text Embedding Model for Music Retrieval

MuLan: A Joint Embedding of Music Audio and Natural Language

We present the first attempt at a new generation of acoustic models that link music audio directly to unconstrained natural language music descriptions.

The resulting audio-text representation subsumes existing ontologies while graduating to true zero-shot functionalities.

We demonstrate the versatility of the embeddings with a range of experiments including transfer learning, zero-shot music tagging, language understanding in the music domain, and cross-modal retrieval applications.

Authors

Qingqing Huang, Aren Jansen, Joonseok Lee, Ravi Ganti, Judith Yue Li, Daniel P. W. Ellis

◐ Recommended Follows

◐ Latest Activity