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

📅 2024-07-16
🏛️ arXiv.org
📈 Citations: 1
Influential: 0
📄 PDF

career value

192K/year
🤖 AI Summary
This study investigates the potential of body-conducted speech (BCS) sensing for privacy-enhancing wearable interaction. To address the lack of standardized, GDPR-compliant BCS benchmarks, we introduce Vibravox—the first multilingual, multimodal, GDPR-aligned French BCS dataset—comprising 45 hours of synchronized recordings from 188 speakers in a 3D higher-order Ambisonics acoustic field. We systematically integrate five BCS sensor types—including ear-canal microphones and bone/throat-conduction transducers—and co-register each with air-conducted reference speech. Leveraging the rich spatial and modal diversity, we establish comprehensive benchmarks for automatic speech recognition, speech enhancement, and speaker verification using state-of-the-art deep learning models. Experimental results reveal fundamental trade-offs across sensors in noise robustness, phonetic fidelity, and speaker discriminability, providing empirical grounding for cross-modal speech modeling. All data and baseline code are publicly released, filling a critical gap in standardized BCS evaluation.

Technology Category

Application Category

📝 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 of speech samples and physiological sounds recorded by 188 participants under different acoustic conditions imposed by an 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.
Problem

Research questions and friction points this paper is trying to address.

Evaluates speech recognition using body-conduction sensors.
Compares speech enhancement across different audio sensors.
Assesses speaker verification with varied acoustic conditions.
Innovation

Methods, ideas, or system contributions that make the work stand out.

Body-conduction audio sensors
High order ambisonics 3D spatializer
State-of-the-art speech-related task models
🔎 Similar Papers
No similar papers found.
J
J. Hauret
Laboratoire de Mécanique des Structures et des Systèmes Couplés, Conservatoire national des arts et métiers, HESAM Université, 75003 Paris, France
M
Malo Olivier
Laboratoire de Mécanique des Structures et des Systèmes Couplés, Conservatoire national des arts et métiers, HESAM Université, 75003 Paris, France
T
Thomas Joubaud
Department of Acoustics and Soldier Protection, French-German Research Institute of Saint-Louis (ISL)
C
C. Langrenne
Laboratoire de Mécanique des Structures et des Systèmes Couplés, Conservatoire national des arts et métiers, HESAM Université, 75003 Paris, France
S
Sarah Poirée
Laboratoire de Mécanique des Structures et des Systèmes Couplés, Conservatoire national des arts et métiers, HESAM Université, 75003 Paris, France
V
V. Zimpfer
Department of Acoustics and Soldier Protection, French-German Research Institute of Saint-Louis (ISL)
É
É. Bavu
Laboratoire de Mécanique des Structures et des Systèmes Couplés, Conservatoire national des arts et métiers, HESAM Université, 75003 Paris, France