Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors

TL;DR

Vibravox is a comprehensive GDPR-compliant dataset of French speech and physiological sounds captured with multiple body-conduction sensors and airborne microphones, enabling research on speech recognition, enhancement, and verification.

Contribution

The paper introduces Vibravox, a novel dataset with diverse sensor recordings and annotations, facilitating advanced research in body-conduction audio processing.

Findings

Sensor-specific performance insights for speech tasks

Comparison of body-conduction and airborne microphone data

Evaluation of state-of-the-art models on new sensor data

Abstract

Vibravox is a dataset compliant with the General Data Protection Regulation (GDPR) containing audio recordings using five different body-conduction audio sensors: two in-ear microphones, two bone conduction vibration pickups, and a laryngophone. The dataset also includes audio data from an airborne microphone used as a reference. The Vibravox corpus contains 45 hours per sensor of speech samples and physiological sounds recorded by 188 participants under different acoustic conditions imposed by a high order ambisonics 3D spatializer. Annotations about the recording conditions and linguistic transcriptions are also included in the corpus. We conducted a series of experiments on various speech-related tasks, including speech recognition, speech enhancement, and speaker verification. These experiments were carried out using state-of-the-art models to evaluate and compare their performances on signals captured by the different audio sensors offered by the Vibravox dataset, with the aim of gaining a better grasp of their individual characteristics.