Introduces a universal real-time speech enhancement model with controllable algorithmic latency via parallel convolutional layers and computational latency via early exits, using a two-stage training approach.
Diffusion buffer for online generative speech enhancement
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
A streaming flow-matching model performs real-time generative speech restoration across multiple tasks at 48 ms latency with state-of-the-art quality.
citing papers explorer
-
One Model, Many Latencies: Universal Speech Enhancement for Diverse Real-Time Applications
Introduces a universal real-time speech enhancement model with controllable algorithmic latency via parallel convolutional layers and computational latency via early exits, using a two-stage training approach.
-
Real-Time Streamable Generative Speech Restoration with Flow Matching
A streaming flow-matching model performs real-time generative speech restoration across multiple tasks at 48 ms latency with state-of-the-art quality.