Inference and Denoise: Causal Inference-based Neural Speech Enhancement
Abstract
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.
Cite
@article{arxiv.2211.01189,
title = {Inference and Denoise: Causal Inference-based Neural Speech Enhancement},
author = {Tsun-An Hsieh and Chao-Han Huck Yang and Pin-Yu Chen and Sabato Marco Siniscalchi and Yu Tsao},
journal= {arXiv preprint arXiv:2211.01189},
year = {2022}
}
Comments
Submitted to ICASSP 2023