Communication Dans Un Congrès Année : 2025

Evaluating Multichannel Speech Enhancement Algorithms at the Phoneme Scale Across Genders

Résumé

Multichannel speech enhancement algorithms are essential for improving the intelligibility of speech signals in noisy environments. These algorithms are usually evaluated at the utterance level, but this approach overlooks the disparities in acoustic characteristics that are observed in different phoneme categories and between male and female speakers. In this paper, we investigate the impact of gender and phonetic content on speech enhancement algorithms. We motivate this approach by outlining phoneme-and gender-specific spectral features. Our experiments reveal that while utterance-level differences between genders are minimal, significant variations emerge at the phoneme level. Results show that the tested algorithms better reduce interference with fewer artifacts on female speech, particularly in plosives, fricatives, and vowels. Additionally, they demonstrate greater performance for female speech in terms of perceptual and speech recognition metrics.

Fichier principal
Vignette du fichier
evaluating-multichannel-speech-enhancement-at-the-phoneme-scale-across-gender (1).pdf (1.19 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05328713 , version 1 (23-10-2025)

Licence

Identifiants

Citer

Nasser-Eddine Monir, Paul Magron, Romain Serizel. Evaluating Multichannel Speech Enhancement Algorithms at the Phoneme Scale Across Genders. 33rd European Signal Processing Conference, Sep 2025, Palerme, Italy. ⟨10.48550/arXiv.2506.18691⟩. ⟨hal-05328713⟩
248 Consultations
116 Téléchargements

Altmetric

Partager

  • More