{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/vibravox-a-dataset-of-french-speech-captured","title":"Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors","arxiv_id":"2407.11828","date":"2024-07-16","proceeding":null,"authors":["Julien Hauret","Malo Olivier","Thomas Joubaud","Christophe Langrenne","Sarah Poirée","Véronique Zimpfer","Éric Bavu"],"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.","url_abs":"https://arxiv.org/abs/2407.11828v4","url_pdf":"https://arxiv.org/pdf/2407.11828v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"vibravox-a-dataset-of-french-speech-captured","repo_url":"https://github.com/jhauret/vibravox","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"automatic-phoneme-recognition","task_name":"Automatic Phoneme Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"bandwidth-extension","task_name":"Bandwidth Extension"},{"task_slug":"speaker-verification","task_name":"Speaker Verification"},{"task_slug":"speech-enhancement","task_name":"Speech Enhancement"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[{"slug":"vibravox-forehead-accelerometer","name":"VibraVox (forehead accelerometer)","full_name":""},{"slug":"vibravox-headset-microphone","name":"VibraVox (headset microphone)","full_name":""},{"slug":"vibravox","name":"VibraVox (rigid in-ear microphone)","full_name":""},{"slug":"vibravox-soft-in-ear-microphone","name":"VibraVox (soft in-ear microphone)","full_name":""},{"slug":"vibravox-temple-vibration-pickup","name":"VibraVox (temple vibration pickup)","full_name":""},{"slug":"vibravox-throat-microphone","name":"VibraVox (throat microphone)","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/automatic-phoneme-recognition-on-vibravox-1","task":"Automatic Phoneme Recognition","dataset":"VibraVox (forehead accelerometer)","model":"medium wav2vec2.0","rank_in_archive_order":1,"of":1,"metrics":{"Test PER":"0.046"},"uses_additional_data":false},{"leaderboard":"/sota/automatic-phoneme-recognition-on-vibravox","task":"Automatic Phoneme Recognition","dataset":"VibraVox (headset microphone)","model":"medium wav2vec2.0","rank_in_archive_order":1,"of":1,"metrics":{"Test PER":"0.028"},"uses_additional_data":false},{"leaderboard":"/sota/automatic-phoneme-recognition-on-vibravox-3","task":"Automatic Phoneme Recognition","dataset":"VibraVox (rigid in-ear microphone)","model":"medium wav2vec2.0","rank_in_archive_order":1,"of":1,"metrics":{"Test PER":"0.045"},"uses_additional_data":false},{"leaderboard":"/sota/automatic-phoneme-recognition-on-vibravox-2","task":"Automatic Phoneme Recognition","dataset":"VibraVox (soft in-ear microphone)","model":"medium wav2vec2.0","rank_in_archive_order":1,"of":1,"metrics":{"Test PER":"0.041"},"uses_additional_data":false},{"leaderboard":"/sota/automatic-phoneme-recognition-on-vibravox-5","task":"Automatic Phoneme Recognition","dataset":"VibraVox (temple vibration pickup)","model":"medium wav2vec2.0","rank_in_archive_order":1,"of":1,"metrics":{"Test PER":"0.142"},"uses_additional_data":false},{"leaderboard":"/sota/automatic-phoneme-recognition-on-vibravox-4","task":"Automatic Phoneme Recognition","dataset":"VibraVox (throat microphone)","model":"medium wav2vec2.0","rank_in_archive_order":1,"of":1,"metrics":{"Test PER":"0.073"},"uses_additional_data":false},{"leaderboard":"/sota/bandwidth-extension-on-vibravox-forehead","task":"Bandwidth Extension","dataset":"VibraVox (forehead accelerometer)","model":"Configurable EBEN (M=4, P=4, Q=4)","rank_in_archive_order":1,"of":1,"metrics":{"EER (ECAPA2)":"0.0183","Noresqua-MOS":"4.250","PER (wav2vec2)":"0.091","STOI":"0.855"},"uses_additional_data":false},{"leaderboard":"/sota/bandwidth-extension-on-vibravox","task":"Bandwidth Extension","dataset":"VibraVox (rigid in-ear microphone)","model":"Configurable EBEN (M=4, P=2, Q=4)","rank_in_archive_order":1,"of":1,"metrics":{"EER (ECAPA2)":"0.0364","Noresqua-MOS":"4.285","PER (wav2vec2)":"0.084","STOI":"0.877"},"uses_additional_data":false},{"leaderboard":"/sota/bandwidth-extension-on-vibravox-soft-in-ear","task":"Bandwidth Extension","dataset":"VibraVox (soft in-ear microphone)","model":"Configurable EBEN (M=4, P=2, Q=4)","rank_in_archive_order":1,"of":1,"metrics":{"EER (ECAPA2)":"0.0488","Noresqua-MOS":"4.331","PER (wav2vec2)":"0.087","STOI":"0.868"},"uses_additional_data":false},{"leaderboard":"/sota/bandwidth-extension-on-vibravox-temple","task":"Bandwidth Extension","dataset":"VibraVox (temple vibration pickup)","model":"Configurable EBEN (M=4, P=1, Q=4)","rank_in_archive_order":1,"of":1,"metrics":{"EER (ECAPA2)":"0.1622","Noresqua-MOS":"3.632","PER (wav2vec2)":"0.391","STOI":"0.763"},"uses_additional_data":false},{"leaderboard":"/sota/bandwidth-extension-on-vibravox-throat","task":"Bandwidth Extension","dataset":"VibraVox (throat microphone)","model":"Configurable EBEN (M=4, P=2, Q=4)","rank_in_archive_order":1,"of":1,"metrics":{"EER (ECAPA2)":"0.0847","Noresqua-MOS":"3.862","PER (wav2vec2)":"0.179","STOI":"0.834"},"uses_additional_data":false},{"leaderboard":"/sota/speaker-verification-on-vibravox-forehead","task":"Speaker Verification","dataset":"VibraVox (forehead accelerometer)","model":"ECAPA2","rank_in_archive_order":1,"of":1,"metrics":{"Test EER":"0.009","Test min-DCF":"0.06"},"uses_additional_data":false},{"leaderboard":"/sota/speaker-verification-on-vibravox-headset","task":"Speaker Verification","dataset":"VibraVox (headset microphone)","model":"ECAPA2","rank_in_archive_order":1,"of":1,"metrics":{"Test EER":"0.0026","Test min-DCF":"0.02"},"uses_additional_data":false},{"leaderboard":"/sota/speaker-verification-on-vibravox-rigid-in-ear","task":"Speaker Verification","dataset":"VibraVox (rigid in-ear microphone)","model":"ECAPA2","rank_in_archive_order":1,"of":1,"metrics":{"Test EER":"0.0316","Test min-DCF":"0.21"},"uses_additional_data":false},{"leaderboard":"/sota/speaker-verification-on-vibravox-soft-in-ear","task":"Speaker Verification","dataset":"VibraVox (soft in-ear microphone)","model":"ECAPA2","rank_in_archive_order":1,"of":1,"metrics":{"Test EER":"0.0172","Test min-DCF":"0.10"},"uses_additional_data":false},{"leaderboard":"/sota/speaker-verification-on-vibravox-temple","task":"Speaker Verification","dataset":"VibraVox (temple vibration pickup)","model":"ECAPA2","rank_in_archive_order":1,"of":1,"metrics":{"Test EER":"0.08","Test min-DCF":"0.58"},"uses_additional_data":false},{"leaderboard":"/sota/speaker-verification-on-vibravox-throat","task":"Speaker Verification","dataset":"VibraVox (throat microphone)","model":"ECAPA2","rank_in_archive_order":1,"of":1,"metrics":{"Test EER":"0.0353","Test min-DCF":"0.20"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.11828","atlas_url":"https://app.syntology.ai/?focus=2407.11828","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2407.11828"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2407.11828\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2407.11828"},"call":"get_concepts_for_paper(arxiv_id=\"2407.11828\")"}],"by_repo":[{"repo":"jhauret/vibravox","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"76cf4283dfa6c6162877e55188aa6f7af4bcf6a93b9058b1a4fcdd7d4c314c09","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}