all AI news
MuLan: A Joint Embedding of Music Audio and Natural Language. (arXiv:2208.12415v1 [eess.AS])
Aug. 29, 2022, 1:13 a.m. | Qingqing Huang, Aren Jansen, Joonseok Lee, Ravi Ganti, Judith Yue Li, Daniel P. W. Ellis
cs.CL 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 / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Senior ML Researcher - 3D Geometry Processing | 3D Shape Generation | 3D Mesh Data
@ Promaton | Europe
Senior AI Engineer, EdTech (Remote)
@ Lightci | Toronto, Ontario
Data Scientist for Salesforce Applications
@ ManTech | 781G - Customer Site,San Antonio,TX
AI Research Scientist
@ Gridmatic | Cupertino, CA
Data Engineer
@ Global Atlantic Financial Group | Boston, Massachusetts, United States
Machine Learning Engineer - Conversation AI
@ DoorDash | Sunnyvale, CA; San Francisco, CA; Seattle, WA; Los Angeles, CA