FLOWER: Flow-Based Estimated Gaussian Guidance for General Speech Restoration

TL;DR

FLOWER is a new method that uses Gaussian guidance via normalizing flows to improve speech restoration, providing precise control and better performance across tasks.

Contribution

It introduces a novel conditioning technique that integrates Gaussian guidance into generative models for speech restoration, enhancing control and effectiveness.

Findings

Improved speech restoration performance across multiple tasks

Effective integration of Gaussian guidance into generative frameworks

Demonstrated superiority over existing methods

Abstract

We introduce FLOWER, a novel conditioning method designed for speech restoration that integrates Gaussian guidance into generative frameworks. By transforming clean speech into a predefined prior distribution (e.g., Gaussian distribution) using a normalizing flow network, FLOWER extracts critical information to guide generative models. This guidance is incorporated into each block of the generative network, enabling precise restoration control. Experimental results demonstrate the effectiveness of FLOWER in improving performance across various general speech restoration tasks.