This website curates the latest high-impact audio machine learning papers from arXiv, organized by audio subcategories and analyzed for relevance and technical significance.
My name is Michael Chinen, and I'm interested in speech and audio research for my job and for fun! I found myself trying to keep up with current research, but the firehose was too hard to drink from. I also made longevitypapers.com which tracks another interest of mine.
Audio ML papers are automatically fetched from arXiv (categories: eess.AS, cs.SD) and analyzed using advanced language models to assess their technical contribution, novelty, and potential impact. Only papers scoring above our quality threshold are featured. Each paper displayed undergoes automated full text analysis after passing an abstract-only analysis.