Interspeech 2022 paper: “PodcastMix: A dataset for separating music and speech in podcasts” By Jordi Pons in Conferences, Datasets, Deep learning, Paper is out July 18, 2022 Today we release “PodcastMix”, a dataset for separating music and speech in podcasts: websitearXiv papertrained separation models at GitHubdownload dataset at Zenodo