SNAC: Revision history

Jump to navigation Jump to search

Diff selection: Mark the radio buttons of the revisions to compare and hit enter or the button at the bottom.
Legend: (cur) = difference with latest revision, (prev) = difference with preceding revision, m = minor edit.

23 December 2025

  • curprev 03:4403:44, 23 December 2025‎ Ttswikiadmin talk contribs‎ 3,314 bytes +3,314‎ Created page with "'''SNAC''' (Multi-Scale Neural Audio Codec) is a neural audio codec that introduces multi-scale temporal quantization for efficient audio compression. It was presented at the NeurIPS 2024 Workshop on AI-Driven Speech, Music, and Sound Generation by researchers from Papla Media and ETH Zurich. === Overview === Neural audio codecs have recently gained popularity because they can represent audio signals with high fidelity at very low bitrates, making it feasible to use..." Tag: Visual edit: Switched
Retrieved from "https://tts.wiki/index.php/SNAC"