A Phoneme-Scale Assessment of Multichannel Speech Enhancement Algorithms
Trends in Hearing · 2024
DOI: 10.1177/23312165241292205 ↗Kurz gefasst
Fachartikel in der Zeitschrift Trends in Hearing, 2024. Verfasst von Nasser-Eddine Monir und 2 weiteren Autor:innen. Beteiligte Einrichtung: Université de Lorraine, CNRS, Inria, Loria, Nancy, France. Hauptthemen laut MEDLINE: Algorithms, Speech Intelligibility, Noise, Speech Perception. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Agence Nationale de la Recherche.
Abstract (Originalsprache)
In the intricate acoustic landscapes where speech intelligibility is challenged by noise and reverberation, multichannel speech enhancement emerges as a promising solution for individuals with hearing loss. Such algorithms are commonly evaluated at the utterance scale. However, this approach overlooks the granular acoustic nuances revealed by phoneme-specific analysis, potentially obscuring key insights into their performance. This paper presents an in-depth phoneme-scale evaluation of three state-of-the-art multichannel speech enhancement algorithms. These algorithms—filter-and-sum network, minimum variance distortionless response, and Tango—are here extensively evaluated across different noise conditions and spatial setups, employing realistic acoustic simulations with measured room impulse responses, and leveraging diversity offered by multiple microphones in a binaural hearing setup. The study emphasizes the fine-grained phoneme-scale analysis, revealing that while some phonemes like plosives are heavily impacted by environmental acoustics and challenging to deal with by the algorithms, others like nasals and sibilants see substantial improvements after enhancement. These investigations demonstrate important improvements in phoneme clarity in noisy conditions, with insights that could drive the development of more personalized and phoneme-aware hearing aid technologies. Additionally, while this study provides extensive data on the physical metrics of processed speech, these physical metrics do not necessarily imitate human perceptions of speech, and the impact of the findings presented would have to be investigated through listening tests.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Université de Lorraine, CNRS, Inria, Loria, Nancy, France.
ORCID-Profile: Nasser-Eddine Monir, Paul Magron
Förderung
- Agence Nationale de la Recherche
Zitieren
APA
Monir, N. E., Magron, P., & Serizel, R. (2024). A Phoneme-Scale Assessment of Multichannel Speech Enhancement Algorithms. Trends in Hearing. https://doi.org/10.1177/23312165241292205
Vancouver
Monir NE, Magron P, Serizel R. A Phoneme-Scale Assessment of Multichannel Speech Enhancement Algorithms. Trends in Hearing. 2024. doi:10.1177/23312165241292205
BibTeX
@article{Monir2024,
author = {Monir, Nasser-Eddine and Magron, Paul and Serizel, Romain},
title = {A Phoneme-Scale Assessment of Multichannel Speech Enhancement Algorithms},
journal = {Trends in Hearing},
year = {2024},
doi = {10.1177/23312165241292205}
}
EUVIMED