{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:G4L455RA5FFENRNPQZQTP3RYQD","short_pith_number":"pith:G4L455RA","schema_version":"1.0","canonical_sha256":"3717cef620e94a46c5af866137ee3880d27aa71e107c2b9a3359bf105bb66351","source":{"kind":"arxiv","id":"2107.13616","version":2},"attestation_state":"computed","paper":{"title":"Proposal-based Few-shot Sound Event Detection for Speech and Environmental Sounds with Perceivers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","cs.SD"],"primary_cat":"eess.AS","authors_text":"Brian Hutchinson, Chris Daw, Lauren Phillips, Logan Sizemore, Piper Wolters","submitted_at":"2021-07-28T19:46:55Z","abstract_excerpt":"Many applications involve detecting and localizing specific sound events within long, untrimmed documents, including keyword spotting, medical observation, and bioacoustic monitoring for conservation. Deep learning techniques often set the state-of-the-art for these tasks. However, for some types of events, there is insufficient labeled data to train such models. In this paper, we propose a region proposal-based approach to few-shot sound event detection utilizing the Perceiver architecture. Motivated by a lack of suitable benchmark datasets, we generate two new few-shot sound event localizati"},"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":"2107.13616","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-07-28T19:46:55Z","cross_cats_sorted":["cs.NE","cs.SD"],"title_canon_sha256":"739b899ae8a46cb8939d33e1f485186d54df70e6c67ca210ff5079d55e2cea02","abstract_canon_sha256":"4818cc321cb54083f6f0e8d74659269434734a5ba8cb10ee27debe2b9a96467b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:22.380611Z","signature_b64":"JKp2mqklm7aalfBAtE4Wj6TpQJGTqjTVY2KQ47ib9kvzkKwylzqV+FkJP/Ikf4C0Bc07dx7Jvy7HMwaZq5A7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3717cef620e94a46c5af866137ee3880d27aa71e107c2b9a3359bf105bb66351","last_reissued_at":"2026-07-05T07:27:22.380112Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:22.380112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Proposal-based Few-shot Sound Event Detection for Speech and Environmental Sounds with Perceivers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","cs.SD"],"primary_cat":"eess.AS","authors_text":"Brian Hutchinson, Chris Daw, Lauren Phillips, Logan Sizemore, Piper Wolters","submitted_at":"2021-07-28T19:46:55Z","abstract_excerpt":"Many applications involve detecting and localizing specific sound events within long, untrimmed documents, including keyword spotting, medical observation, and bioacoustic monitoring for conservation. Deep learning techniques often set the state-of-the-art for these tasks. However, for some types of events, there is insufficient labeled data to train such models. In this paper, we propose a region proposal-based approach to few-shot sound event detection utilizing the Perceiver architecture. Motivated by a lack of suitable benchmark datasets, we generate two new few-shot sound event localizati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.13616","kind":"arxiv","version":2},"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/2107.13616/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":"2107.13616","created_at":"2026-07-05T07:27:22.380170+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.13616v2","created_at":"2026-07-05T07:27:22.380170+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.13616","created_at":"2026-07-05T07:27:22.380170+00:00"},{"alias_kind":"pith_short_12","alias_value":"G4L455RA5FFE","created_at":"2026-07-05T07:27:22.380170+00:00"},{"alias_kind":"pith_short_16","alias_value":"G4L455RA5FFENRNP","created_at":"2026-07-05T07:27:22.380170+00:00"},{"alias_kind":"pith_short_8","alias_value":"G4L455RA","created_at":"2026-07-05T07:27:22.380170+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.01253","citing_title":"animal2vec and MeerKAT: A self-supervised transformer for rare-event raw audio input and a large-scale reference dataset for bioacoustics","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G4L455RA5FFENRNPQZQTP3RYQD","json":"https://pith.science/pith/G4L455RA5FFENRNPQZQTP3RYQD.json","graph_json":"https://pith.science/api/pith-number/G4L455RA5FFENRNPQZQTP3RYQD/graph.json","events_json":"https://pith.science/api/pith-number/G4L455RA5FFENRNPQZQTP3RYQD/events.json","paper":"https://pith.science/paper/G4L455RA"},"agent_actions":{"view_html":"https://pith.science/pith/G4L455RA5FFENRNPQZQTP3RYQD","download_json":"https://pith.science/pith/G4L455RA5FFENRNPQZQTP3RYQD.json","view_paper":"https://pith.science/paper/G4L455RA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.13616&json=true","fetch_graph":"https://pith.science/api/pith-number/G4L455RA5FFENRNPQZQTP3RYQD/graph.json","fetch_events":"https://pith.science/api/pith-number/G4L455RA5FFENRNPQZQTP3RYQD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G4L455RA5FFENRNPQZQTP3RYQD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G4L455RA5FFENRNPQZQTP3RYQD/action/storage_attestation","attest_author":"https://pith.science/pith/G4L455RA5FFENRNPQZQTP3RYQD/action/author_attestation","sign_citation":"https://pith.science/pith/G4L455RA5FFENRNPQZQTP3RYQD/action/citation_signature","submit_replication":"https://pith.science/pith/G4L455RA5FFENRNPQZQTP3RYQD/action/replication_record"}},"created_at":"2026-07-05T07:27:22.380170+00:00","updated_at":"2026-07-05T07:27:22.380170+00:00"}