Toward Universal Speech Enhancement for Diverse Input Conditions

TL;DR

This paper introduces a universal speech enhancement model capable of handling diverse input conditions such as different microphone setups, signal lengths, and sampling frequencies, demonstrating strong performance across multiple datasets.

Contribution

The paper proposes the first single speech enhancement model that is independent of microphone channels, signal lengths, and sampling frequencies, and establishes a comprehensive benchmark for diverse conditions.

Findings

The model effectively handles various input conditions.

Strong performance across multiple datasets.

A new universal speech enhancement benchmark.

Abstract

The past decade has witnessed substantial growth of data-driven speech enhancement (SE) techniques thanks to deep learning. While existing approaches have shown impressive performance in some common datasets, most of them are designed only for a single condition (e.g., single-channel, multi-channel, or a fixed sampling frequency) or only consider a single task (e.g., denoising or dereverberation). Currently, there is no universal SE approach that can effectively handle diverse input conditions with a single model. In this paper, we make the first attempt to investigate this line of research. First, we devise a single SE model that is independent of microphone channels, signal lengths, and sampling frequencies. Second, we design a universal SE benchmark by combining existing public corpora with multiple conditions. Our experiments on a wide range of datasets show that the proposed single model can successfully handle diverse conditions with strong performance.