{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:GZ3GA5SY4HAEIRSTDI6YBWEKZT","short_pith_number":"pith:GZ3GA5SY","schema_version":"1.0","canonical_sha256":"3676607658e1c04446531a3d80d88accca256a7aaa7346879a40ce99ef3fd771","source":{"kind":"arxiv","id":"1604.00861","version":1},"attestation_state":"computed","paper":{"title":"Recurrent Neural Networks for Polyphonic Sound Event Detection in Real Life Recordings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.SD","authors_text":"Giambattista Parascandolo, Heikki Huttunen, Tuomas Virtanen","submitted_at":"2016-04-04T13:54:09Z","abstract_excerpt":"In this paper we present an approach to polyphonic sound event detection in real life recordings based on bi-directional long short term memory (BLSTM) recurrent neural networks (RNNs). A single multilabel BLSTM RNN is trained to map acoustic features of a mixture signal consisting of sounds from multiple classes, to binary activity indicators of each event class. Our method is tested on a large database of real-life recordings, with 61 classes (e.g. music, car, speech) from 10 different everyday contexts. The proposed method outperforms previous approaches by a large margin, and the results a"},"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":"1604.00861","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2016-04-04T13:54:09Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"cc27a162d90952db8a133eff99bf477476714052af282dc295b8499117957325","abstract_canon_sha256":"7575114bcf081d54e05f2da9349d6772e72917d0c82b655c8634ef26d343be2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:58:33.771626Z","signature_b64":"ovTaKDY/osQiNr1ovuweKGCHvR7tbbBK7m/6f8sIEYsfsowdV68buFvwQvIBeybpRofLbYdg2LtkPNMdD0leCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3676607658e1c04446531a3d80d88accca256a7aaa7346879a40ce99ef3fd771","last_reissued_at":"2026-05-18T00:58:33.770922Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:58:33.770922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recurrent Neural Networks for Polyphonic Sound Event Detection in Real Life Recordings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.SD","authors_text":"Giambattista Parascandolo, Heikki Huttunen, Tuomas Virtanen","submitted_at":"2016-04-04T13:54:09Z","abstract_excerpt":"In this paper we present an approach to polyphonic sound event detection in real life recordings based on bi-directional long short term memory (BLSTM) recurrent neural networks (RNNs). A single multilabel BLSTM RNN is trained to map acoustic features of a mixture signal consisting of sounds from multiple classes, to binary activity indicators of each event class. Our method is tested on a large database of real-life recordings, with 61 classes (e.g. music, car, speech) from 10 different everyday contexts. The proposed method outperforms previous approaches by a large margin, and the results a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.00861","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":""},"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":"1604.00861","created_at":"2026-05-18T00:58:33.770998+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.00861v1","created_at":"2026-05-18T00:58:33.770998+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.00861","created_at":"2026-05-18T00:58:33.770998+00:00"},{"alias_kind":"pith_short_12","alias_value":"GZ3GA5SY4HAE","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_16","alias_value":"GZ3GA5SY4HAEIRST","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_8","alias_value":"GZ3GA5SY","created_at":"2026-05-18T12:30:19.053100+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/GZ3GA5SY4HAEIRSTDI6YBWEKZT","json":"https://pith.science/pith/GZ3GA5SY4HAEIRSTDI6YBWEKZT.json","graph_json":"https://pith.science/api/pith-number/GZ3GA5SY4HAEIRSTDI6YBWEKZT/graph.json","events_json":"https://pith.science/api/pith-number/GZ3GA5SY4HAEIRSTDI6YBWEKZT/events.json","paper":"https://pith.science/paper/GZ3GA5SY"},"agent_actions":{"view_html":"https://pith.science/pith/GZ3GA5SY4HAEIRSTDI6YBWEKZT","download_json":"https://pith.science/pith/GZ3GA5SY4HAEIRSTDI6YBWEKZT.json","view_paper":"https://pith.science/paper/GZ3GA5SY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.00861&json=true","fetch_graph":"https://pith.science/api/pith-number/GZ3GA5SY4HAEIRSTDI6YBWEKZT/graph.json","fetch_events":"https://pith.science/api/pith-number/GZ3GA5SY4HAEIRSTDI6YBWEKZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GZ3GA5SY4HAEIRSTDI6YBWEKZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GZ3GA5SY4HAEIRSTDI6YBWEKZT/action/storage_attestation","attest_author":"https://pith.science/pith/GZ3GA5SY4HAEIRSTDI6YBWEKZT/action/author_attestation","sign_citation":"https://pith.science/pith/GZ3GA5SY4HAEIRSTDI6YBWEKZT/action/citation_signature","submit_replication":"https://pith.science/pith/GZ3GA5SY4HAEIRSTDI6YBWEKZT/action/replication_record"}},"created_at":"2026-05-18T00:58:33.770998+00:00","updated_at":"2026-05-18T00:58:33.770998+00:00"}