Comparing human and machine speech recognition in noise with QuickSIN
JASA Express Letters · 2024
DOI: 10.1121/10.0028612 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift JASA Express Letters, 2024. Verfasst von Malcolm Slaney und 1 weiteren Autor:innen. Beteiligte Einrichtung: Center for Computer Research in Music and Acoustics, Stanford University, Stanford, California 94305, USA. Hauptthemen laut MEDLINE: Noise, Speech Recognition Software, Speech Perception, Signal-To-Noise Ratio. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
A test is proposed to characterize the performance of speech recognition systems. The QuickSIN test is used by audiologists to measure the ability of humans to recognize continuous speech in noise. This test yields the signal-to-noise ratio at which individuals can correctly recognize 50% of the keywords in low-context sentences. It is argued that a metric for automatic speech recognizers will ground the performance of automatic speech-in-noise recognizers to human abilities. Here, it is demonstrated that the performance of modern recognizers, built using millions of hours of unsupervised training data, is anywhere from normal to mildly impaired in noise compared to human participants.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Center for Computer Research in Music and Acoustics, Stanford University, Stanford, California 94305, USA.
- Department of Otolaryngology-Head and Neck Surgery, Stanford University, Stanford, California 94305, USAmalcolm@ieee.org, fitzmb@stanford.edu.
ORCID-Profile: Malcolm Slaney, Matthew B Fitzgerald
Zitieren
APA
Slaney, M., & Fitzgerald, M. B. (2024). Comparing human and machine speech recognition in noise with QuickSIN. JASA Express Letters. https://doi.org/10.1121/10.0028612
Vancouver
Slaney M, Fitzgerald MB. Comparing human and machine speech recognition in noise with QuickSIN. JASA Express Letters. 2024. doi:10.1121/10.0028612
BibTeX
@article{Slaney2024,
author = {Slaney, Malcolm and Fitzgerald, Matthew B},
title = {Comparing human and machine speech recognition in noise with QuickSIN},
journal = {JASA Express Letters},
year = {2024},
doi = {10.1121/10.0028612}
}
EUVIMED