Algorithm to suppress scanner noise in recorded speech during functional magnetic resonance imaging

TL;DR

This paper presents an adaptive filtering algorithm that effectively suppresses scanner noise in speech recordings during fMRI, enabling clearer speech monitoring and analysis in real-time.

Contribution

The novel adaptive filtering method combines time and frequency domain techniques to significantly improve speech signal quality in noisy fMRI environments.

Findings

Increased signal-to-noise ratio in recorded speech

Real-time noise suppression suitable for clinical use

Enhanced speech recordings for offline analysis

Abstract

The high-intensity, repetitive noise associated with functional magnetic resonance imaging hinders on-line monitoring of subjects' speech and/or recording speech signals suitable for off-line analysis. The proposed algorithm enhances the speech signal by suppressing the scanner noise in the signal recorded by a single-channel microphone. Significant increases in signal-to-noise ratio are achieved using an adaptive filter that combines time and frequency domain elements. In addition to providing a recording suitable for speech analysis, such a real-time system provides an alternative means (to, e.g., the "panic ball") for communication between the patient and the operator during image acquisition.