{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TU35ITHJ3PVASU74O5E7OWFLAD","short_pith_number":"pith:TU35ITHJ","schema_version":"1.0","canonical_sha256":"9d37d44ce9dbea0953fc7749f758ab00d627b5935a88269414599b4a9dd5b542","source":{"kind":"arxiv","id":"2308.12370","version":1},"attestation_state":"computed","paper":{"title":"AdVerb: Visually Guided Audio Dereverberation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Anton Ratnarajah, Dinesh Manocha, Sanjoy Chowdhury, Sreyan Ghosh, Subhrajyoti Dasgupta, Utkarsh Tyagi","submitted_at":"2023-08-23T18:20:59Z","abstract_excerpt":"We present AdVerb, a novel audio-visual dereverberation framework that uses visual cues in addition to the reverberant sound to estimate clean audio. Although audio-only dereverberation is a well-studied problem, our approach incorporates the complementary visual modality to perform audio dereverberation. Given an image of the environment where the reverberated sound signal has been recorded, AdVerb employs a novel geometry-aware cross-modal transformer architecture that captures scene geometry and audio-visual cross-modal relationship to generate a complex ideal ratio mask, which, when applie"},"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":"2308.12370","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-23T18:20:59Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"11ab19482ac1faebf1a2c05d9f9d27756385bdbfa8d2437621b3b409dafb5a59","abstract_canon_sha256":"40ef8ba73d06f65ab15d56ca98092dec4a58e46e1755ac78024e1123e03889de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:11.308071Z","signature_b64":"yboSWmwfIJ/XZEwjCCvc90Zcac0vLJiRHHkTiXxpY7WZNBojXJklmBWwUSmjsApZbb4i6W/r0reTkM8k3EGjBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d37d44ce9dbea0953fc7749f758ab00d627b5935a88269414599b4a9dd5b542","last_reissued_at":"2026-07-05T06:44:11.307546Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:11.307546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdVerb: Visually Guided Audio Dereverberation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Anton Ratnarajah, Dinesh Manocha, Sanjoy Chowdhury, Sreyan Ghosh, Subhrajyoti Dasgupta, Utkarsh Tyagi","submitted_at":"2023-08-23T18:20:59Z","abstract_excerpt":"We present AdVerb, a novel audio-visual dereverberation framework that uses visual cues in addition to the reverberant sound to estimate clean audio. Although audio-only dereverberation is a well-studied problem, our approach incorporates the complementary visual modality to perform audio dereverberation. Given an image of the environment where the reverberated sound signal has been recorded, AdVerb employs a novel geometry-aware cross-modal transformer architecture that captures scene geometry and audio-visual cross-modal relationship to generate a complex ideal ratio mask, which, when applie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12370","kind":"arxiv","version":1},"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/2308.12370/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":"2308.12370","created_at":"2026-07-05T06:44:11.307624+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.12370v1","created_at":"2026-07-05T06:44:11.307624+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12370","created_at":"2026-07-05T06:44:11.307624+00:00"},{"alias_kind":"pith_short_12","alias_value":"TU35ITHJ3PVA","created_at":"2026-07-05T06:44:11.307624+00:00"},{"alias_kind":"pith_short_16","alias_value":"TU35ITHJ3PVASU74","created_at":"2026-07-05T06:44:11.307624+00:00"},{"alias_kind":"pith_short_8","alias_value":"TU35ITHJ","created_at":"2026-07-05T06:44:11.307624+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TU35ITHJ3PVASU74O5E7OWFLAD","json":"https://pith.science/pith/TU35ITHJ3PVASU74O5E7OWFLAD.json","graph_json":"https://pith.science/api/pith-number/TU35ITHJ3PVASU74O5E7OWFLAD/graph.json","events_json":"https://pith.science/api/pith-number/TU35ITHJ3PVASU74O5E7OWFLAD/events.json","paper":"https://pith.science/paper/TU35ITHJ"},"agent_actions":{"view_html":"https://pith.science/pith/TU35ITHJ3PVASU74O5E7OWFLAD","download_json":"https://pith.science/pith/TU35ITHJ3PVASU74O5E7OWFLAD.json","view_paper":"https://pith.science/paper/TU35ITHJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.12370&json=true","fetch_graph":"https://pith.science/api/pith-number/TU35ITHJ3PVASU74O5E7OWFLAD/graph.json","fetch_events":"https://pith.science/api/pith-number/TU35ITHJ3PVASU74O5E7OWFLAD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TU35ITHJ3PVASU74O5E7OWFLAD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TU35ITHJ3PVASU74O5E7OWFLAD/action/storage_attestation","attest_author":"https://pith.science/pith/TU35ITHJ3PVASU74O5E7OWFLAD/action/author_attestation","sign_citation":"https://pith.science/pith/TU35ITHJ3PVASU74O5E7OWFLAD/action/citation_signature","submit_replication":"https://pith.science/pith/TU35ITHJ3PVASU74O5E7OWFLAD/action/replication_record"}},"created_at":"2026-07-05T06:44:11.307624+00:00","updated_at":"2026-07-05T06:44:11.307624+00:00"}