Assessing Speech Intelligibility in Noisy Environments: A Quantitative Analysis

Fuente: Zenodo
Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Anastasiia Kuznetsova and Yulian Petrov
Format: Recurso digital
Veröffentlicht: Zenodo 2021
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866901187474751488
author Anastasiia Kuznetsova and Yulian Petrov
author_facet Anastasiia Kuznetsova and Yulian Petrov
contents <p>Specifics of acoustic signal processing prior partial signal-to-noise ratios estimating when measuring speech intelligibility under noise dominance was studied. A pre-processing algorithm was proposed and tested using real signals. The speech intelligibility was evaluated using three versions of the formant method as well as the speech transmission index. The quality criteria for this test were the closeness of speech intelligibility estimates obtained during predicting and in real measurements, as well as the reliability of detection of a test noise signal against a background of noise interference. The closeness of the measurement and prediction results of speech intelligibility testifies to the reliability of measurements performed using the proposed algorithm. A sufficiently high reliability of signal detection by the threshold method is achieved with a signal-to-noise ratio of at least 0 dB. Key words: measurement, speech intelligibility, word intelligibility, speech transmission index, noise interference ________________________________________________________________________________________</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_19325230
institution Zenodo
language
publishDate 2021
publisher Zenodo
record_format zenodo
spellingShingle Assessing Speech Intelligibility in Noisy Environments: A Quantitative Analysis
Anastasiia Kuznetsova and Yulian Petrov
Computer Engineering
Advanced Computing
Technology
Open Access
<p>Specifics of acoustic signal processing prior partial signal-to-noise ratios estimating when measuring speech intelligibility under noise dominance was studied. A pre-processing algorithm was proposed and tested using real signals. The speech intelligibility was evaluated using three versions of the formant method as well as the speech transmission index. The quality criteria for this test were the closeness of speech intelligibility estimates obtained during predicting and in real measurements, as well as the reliability of detection of a test noise signal against a background of noise interference. The closeness of the measurement and prediction results of speech intelligibility testifies to the reliability of measurements performed using the proposed algorithm. A sufficiently high reliability of signal detection by the threshold method is achieved with a signal-to-noise ratio of at least 0 dB. Key words: measurement, speech intelligibility, word intelligibility, speech transmission index, noise interference ________________________________________________________________________________________</p>
title Assessing Speech Intelligibility in Noisy Environments: A Quantitative Analysis
topic Computer Engineering
Advanced Computing
Technology
Open Access
url https://doi.org/10.5281/zenodo.19325230