ICASSP-2023-24-Papers

Why we included this project

ICASSP's 2023 and 2024 programs were huge, and keeping track of what actually got presented can take more effort than reading the papers themselves. This curated index does that sorting for you: entries are grouped by technical session rather than listed as one long wall of titles, so you can land directly on self-supervised speech learning, diffusion-based speech enhancement, voice conversion, or acoustic scene classification. Where the authors released code, each entry points to it, which saves real time when you want to reproduce a baseline or graft a recent method onto your own work instead of reimplementing from the PDF. The maintainers accept pull requests to close gaps, so the collection keeps growing past a single snapshot of the proceedings. It is a bookmarked reference, not an installable library, but as a survey of where speech and audio research currently stands it is a solid first stop.