Guided Source Separation (GSS) is a popular front-end for distant automatic speech recognition (ASR) systems using spatially distributed microphones. When considering spatially distributed microphones, the choice of reference microphone may have a large influence on the quality of the output signal and the downstream ASR performance. In GSS-based speech enhancement, reference microphone selection is typically performed using the signal-to-noise ratio (SNR), which is optimal for noise reduction but may neglect differences in early-to-late-reverberant ratio (ELR) across microphones. In this paper, we propose two reference microphone selection methods for GSS-based speech enhancement that are based on the normalized ℓp-norm, either using only the normalized ℓp-norm or combining the normalized ℓp-norm and the SNR to account for both differences in SNR and ELR across microphones. Experimental evaluation using a CHiME-8 distant ASR system shows that the proposed ℓp-norm-based methods outperform the baseline method, reducing the macro-average word error rate.
@article{arxiv.2510.27198,
title = {Reference Microphone Selection for Guided Source Separation based on the Normalized L-p Norm},
author = {Anselm Lohmann and Tomohiro Nakatani and Rintaro Ikeshita and Marc Delcroix and Shoko Araki and Simon Doclo},
journal= {arXiv preprint arXiv:2510.27198},
year = {2025}
}