French Listening Tests for the Assessment of Intelligibility, Quality, and Identity of Body-Conducted Speech Enhancement

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Joubaud, Thomas, Hauret, Julien, Zimpfer, Véronique, Bavu, Éric
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914045367418880
author Joubaud, Thomas
Hauret, Julien
Zimpfer, Véronique
Bavu, Éric
author_facet Joubaud, Thomas
Hauret, Julien
Zimpfer, Véronique
Bavu, Éric
contents This study evaluates the Extreme Bandwidth Extension Network (EBEN) model on body-conduction sensors through listening tests. Using the Vibravox dataset, we assess intelligibility with a French Modified Rhyme Test, speech quality with a MUSHRA (MUltiple Stimuli with Hidden Reference and Anchor) protocol and speaker identity preservation with an A/B identification task. The experiments involved male and female speakers recorded with a forehead accelerometer, rigid in-ear and throat microphones. The results confirm that EBEN enhances both speech quality and intelligibility. It slightly degrades speaker identification performance when applied to female speakers' throat microphone recordings. The findings also demonstrate a correlation between Short-Time Objective Intelligibility (STOI) and perceived quality in body-conducted speech, while speaker verification using ECAPA2-TDNN aligns well with identification performance. No tested metric reliably predicts EBEN's effect on intelligibility.
format Preprint
id arxiv_https___arxiv_org_abs_2506_04495
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle French Listening Tests for the Assessment of Intelligibility, Quality, and Identity of Body-Conducted Speech Enhancement
Joubaud, Thomas
Hauret, Julien
Zimpfer, Véronique
Bavu, Éric
Audio and Speech Processing
This study evaluates the Extreme Bandwidth Extension Network (EBEN) model on body-conduction sensors through listening tests. Using the Vibravox dataset, we assess intelligibility with a French Modified Rhyme Test, speech quality with a MUSHRA (MUltiple Stimuli with Hidden Reference and Anchor) protocol and speaker identity preservation with an A/B identification task. The experiments involved male and female speakers recorded with a forehead accelerometer, rigid in-ear and throat microphones. The results confirm that EBEN enhances both speech quality and intelligibility. It slightly degrades speaker identification performance when applied to female speakers' throat microphone recordings. The findings also demonstrate a correlation between Short-Time Objective Intelligibility (STOI) and perceived quality in body-conducted speech, while speaker verification using ECAPA2-TDNN aligns well with identification performance. No tested metric reliably predicts EBEN's effect on intelligibility.
title French Listening Tests for the Assessment of Intelligibility, Quality, and Identity of Body-Conducted Speech Enhancement
topic Audio and Speech Processing
url https://arxiv.org/abs/2506.04495