all AI news
MuLan: A Joint Embedding of Music Audio and Natural Language. (arXiv:2208.12415v1 [eess.AS])
Aug. 29, 2022, 1:12 a.m. | Qingqing Huang, Aren Jansen, Joonseok Lee, Ravi Ganti, Judith Yue Li, Daniel P. W. Ellis
stat.ML updates on arXiv.org arxiv.org
Music tagging and content-based retrieval systems have traditionally been
constructed using pre-defined ontologies covering a rigid set of music
attributes or text queries. This paper presents MuLan: a first attempt at a new
generation of acoustic models that link music audio directly to unconstrained
natural language music descriptions. MuLan takes the form of a two-tower, joint
audio-text embedding model trained using 44 million music recordings (370K
hours) and weakly-associated, free-form text annotations. Through its
compatibility with a wide range of …
arxiv audio embedding language music natural natural language
More from arxiv.org / stat.ML updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Stagista Technical Data Engineer
@ Hager Group | BRESCIA, IT
Data Analytics - SAS, SQL - Associate
@ JPMorgan Chase & Co. | Mumbai, Maharashtra, India