{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ACPLF6VMSQ6NWJZCYUZE627SJF","short_pith_number":"pith:ACPLF6VM","schema_version":"1.0","canonical_sha256":"009eb2faac943cdb2722c5324f6bf249559e4cbc4d243724695a102dd42ef082","source":{"kind":"arxiv","id":"2210.13248","version":3},"attestation_state":"computed","paper":{"title":"Brouhaha: multi-task training for voice activity detection, speech-to-noise ratio, and C50 room acoustics estimation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Alejandrina Cristia, Alodie Boissonnet, Elika Bergelson, Emmanuel Dupoux, Hadrien Titeux, Herv\\'e Bredin, Jade Copet, Marianne M\\'etais, Marvin Lavechin, Morgane Rivi\\`ere","submitted_at":"2022-10-24T13:47:36Z","abstract_excerpt":"Most automatic speech processing systems register degraded performance when applied to noisy or reverberant speech. But how can one tell whether speech is noisy or reverberant? We propose Brouhaha, a neural network jointly trained to extract speech/non-speech segments, speech-to-noise ratios, and C50room acoustics from single-channel recordings. Brouhaha is trained using a data-driven approach in which noisy and reverberant audio segments are synthesized. We first evaluate its performance and demonstrate that the proposed multi-task regime is beneficial. We then present two scenarios illustrat"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2210.13248","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2022-10-24T13:47:36Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"750cd56b3865b46c938bdb860546fb8eabd909001a0339fbc15718aba339aa2a","abstract_canon_sha256":"b7e57250401ab74c51ea94850bcb799b0738c1b89a9fa877c84cb6f7f09ae820"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:53.230103Z","signature_b64":"l0QnqAYci3Uah/d6nRRFHnrA5L8VeggrSZNLfe28cE9ZIjKC8fwqFbBIh1kEFmrbZZna9SVSsc6OUd6L7ZLVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"009eb2faac943cdb2722c5324f6bf249559e4cbc4d243724695a102dd42ef082","last_reissued_at":"2026-07-05T06:13:53.229587Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:53.229587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Brouhaha: multi-task training for voice activity detection, speech-to-noise ratio, and C50 room acoustics estimation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Alejandrina Cristia, Alodie Boissonnet, Elika Bergelson, Emmanuel Dupoux, Hadrien Titeux, Herv\\'e Bredin, Jade Copet, Marianne M\\'etais, Marvin Lavechin, Morgane Rivi\\`ere","submitted_at":"2022-10-24T13:47:36Z","abstract_excerpt":"Most automatic speech processing systems register degraded performance when applied to noisy or reverberant speech. But how can one tell whether speech is noisy or reverberant? We propose Brouhaha, a neural network jointly trained to extract speech/non-speech segments, speech-to-noise ratios, and C50room acoustics from single-channel recordings. Brouhaha is trained using a data-driven approach in which noisy and reverberant audio segments are synthesized. We first evaluate its performance and demonstrate that the proposed multi-task regime is beneficial. We then present two scenarios illustrat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.13248","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.13248/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2210.13248","created_at":"2026-07-05T06:13:53.229652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.13248v3","created_at":"2026-07-05T06:13:53.229652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.13248","created_at":"2026-07-05T06:13:53.229652+00:00"},{"alias_kind":"pith_short_12","alias_value":"ACPLF6VMSQ6N","created_at":"2026-07-05T06:13:53.229652+00:00"},{"alias_kind":"pith_short_16","alias_value":"ACPLF6VMSQ6NWJZC","created_at":"2026-07-05T06:13:53.229652+00:00"},{"alias_kind":"pith_short_8","alias_value":"ACPLF6VM","created_at":"2026-07-05T06:13:53.229652+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03283","citing_title":"SpeakerCard-1M: An Evidence-Grounded Corpus for In-the-Wild Speaker Verification","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ACPLF6VMSQ6NWJZCYUZE627SJF","json":"https://pith.science/pith/ACPLF6VMSQ6NWJZCYUZE627SJF.json","graph_json":"https://pith.science/api/pith-number/ACPLF6VMSQ6NWJZCYUZE627SJF/graph.json","events_json":"https://pith.science/api/pith-number/ACPLF6VMSQ6NWJZCYUZE627SJF/events.json","paper":"https://pith.science/paper/ACPLF6VM"},"agent_actions":{"view_html":"https://pith.science/pith/ACPLF6VMSQ6NWJZCYUZE627SJF","download_json":"https://pith.science/pith/ACPLF6VMSQ6NWJZCYUZE627SJF.json","view_paper":"https://pith.science/paper/ACPLF6VM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.13248&json=true","fetch_graph":"https://pith.science/api/pith-number/ACPLF6VMSQ6NWJZCYUZE627SJF/graph.json","fetch_events":"https://pith.science/api/pith-number/ACPLF6VMSQ6NWJZCYUZE627SJF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ACPLF6VMSQ6NWJZCYUZE627SJF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ACPLF6VMSQ6NWJZCYUZE627SJF/action/storage_attestation","attest_author":"https://pith.science/pith/ACPLF6VMSQ6NWJZCYUZE627SJF/action/author_attestation","sign_citation":"https://pith.science/pith/ACPLF6VMSQ6NWJZCYUZE627SJF/action/citation_signature","submit_replication":"https://pith.science/pith/ACPLF6VMSQ6NWJZCYUZE627SJF/action/replication_record"}},"created_at":"2026-07-05T06:13:53.229652+00:00","updated_at":"2026-07-05T06:13:53.229652+00:00"}