Inference and Denoise: Causal Inference-based Neural Speech Enhancement

by   Tsun-An Hsieh, et al.

This study addresses the speech enhancement (SE) task within the causal inference paradigm by modeling the noise presence as an intervention. Based on the potential outcome framework, the proposed causal inference-based speech enhancement (CISE) separates clean and noisy frames in an intervened noisy speech using a noise detector and assigns both sets of frames to two mask-based enhancement modules (EMs) to perform noise-conditional SE. Specifically, we use the presence of noise as guidance for EM selection during training, and the noise detector selects the enhancement module according to the prediction of the presence of noise for each frame. Moreover, we derived a SE-specific average treatment effect to quantify the causal effect adequately. Experimental evidence demonstrates that CISE outperforms a non-causal mask-based SE approach in the studied settings and has better performance and efficiency than more complex SE models.


Joint Noise Reduction and Listening Enhancement for Full-End Speech Enhancement

Speech enhancement (SE) methods mainly focus on recovering clean speech ...

Perceptual Contrast Stretching on Target Feature for Speech Enhancement

Speech enhancement (SE) performance has improved considerably since the ...

Speech Enhancement Based on Cyclegan with Noise-informed Training

Speech enhancement (SE) approaches can be classified into supervised and...

NASTAR: Noise Adaptive Speech Enhancement with Target-Conditional Resampling

For deep learning-based speech enhancement (SE) systems, the training-te...

A non-causal FFTNet architecture for speech enhancement

In this paper, we suggest a new parallel, non-causal and shallow wavefor...

NADiffuSE: Noise-aware Diffusion-based Model for Speech Enhancement

The goal of speech enhancement (SE) is to eliminate the background inter...

SERIL: Noise Adaptive Speech Enhancement using Regularization-based Incremental Learning

Numerous noise adaptation techniques have been proposed to address the m...

Please sign up or login with your details

Forgot password? Click here to reset