neural audio codec
1 statements across 1 episodes · 1 bullish · 0 bearish · 1 people on the record · first statement Mar 30, 2026 by Pavan Kumar Reddy · across every show →
Everything said about neural audio codec, oldest first
Mar 30, 2026 bullish
Reddy: Continuous flow matching outperforms discrete audio tokens for speech generation
“So the thing we did differently is instead of having this autoregressive K step prediction, we have a flow matching model. Instead of modeling this as a discrete token set, we trained the codec to be both discrete and continuous to have this flexibility. So we…”