{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:P7BB5MBILIM7HZGKUO7DLKTOUC","short_pith_number":"pith:P7BB5MBI","schema_version":"1.0","canonical_sha256":"7fc21eb0285a19f3e4caa3be35aa6ea0a5f72eb304eb4bb0f1a142906b2dba64","source":{"kind":"arxiv","id":"1810.12832","version":1},"attestation_state":"computed","paper":{"title":"General audio tagging with ensembling convolutional neural network and statistical features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Ding, Boqing Zhu, Dezhi Wang, Haibo Mi, Huaimin Wang, Kele Xu, Qiuqiang Kong","submitted_at":"2018-10-30T15:59:28Z","abstract_excerpt":"Audio tagging aims to infer descriptive labels from audio clips. Audio tagging is challenging due to the limited size of data and noisy labels. In this paper, we describe our solution for the DCASE 2018 Task 2 general audio tagging challenge. The contributions of our solution include: We investigated a variety of convolutional neural network architectures to solve the audio tagging task. Statistical features are applied to capture statistical patterns of audio features to improve the classification performance. Ensemble learning is applied to ensemble the outputs from the deep classifiers to u"},"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":"1810.12832","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-30T15:59:28Z","cross_cats_sorted":[],"title_canon_sha256":"89536dc1322a128753a15b5e90511d57600c302af64f1c7e8120687ef62d19c9","abstract_canon_sha256":"5327d8aa41212b6ce61a5636763cc04f7d0afd412aceeab5bef31c65804e07b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:48.188827Z","signature_b64":"kL/S1uMHDAgPcYP2ZoJHpmfTE7D+LCvFyQNTAT+moHodemukf3r+Mf156QRh4fOIA37DpPet3SHwVoz2dVfgAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fc21eb0285a19f3e4caa3be35aa6ea0a5f72eb304eb4bb0f1a142906b2dba64","last_reissued_at":"2026-05-17T23:39:48.188210Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:48.188210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"General audio tagging with ensembling convolutional neural network and statistical features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Ding, Boqing Zhu, Dezhi Wang, Haibo Mi, Huaimin Wang, Kele Xu, Qiuqiang Kong","submitted_at":"2018-10-30T15:59:28Z","abstract_excerpt":"Audio tagging aims to infer descriptive labels from audio clips. Audio tagging is challenging due to the limited size of data and noisy labels. In this paper, we describe our solution for the DCASE 2018 Task 2 general audio tagging challenge. The contributions of our solution include: We investigated a variety of convolutional neural network architectures to solve the audio tagging task. Statistical features are applied to capture statistical patterns of audio features to improve the classification performance. Ensemble learning is applied to ensemble the outputs from the deep classifiers to u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12832","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":"1810.12832","created_at":"2026-05-17T23:39:48.188309+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.12832v1","created_at":"2026-05-17T23:39:48.188309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12832","created_at":"2026-05-17T23:39:48.188309+00:00"},{"alias_kind":"pith_short_12","alias_value":"P7BB5MBILIM7","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"P7BB5MBILIM7HZGK","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"P7BB5MBI","created_at":"2026-05-18T12:32:43.782077+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/P7BB5MBILIM7HZGKUO7DLKTOUC","json":"https://pith.science/pith/P7BB5MBILIM7HZGKUO7DLKTOUC.json","graph_json":"https://pith.science/api/pith-number/P7BB5MBILIM7HZGKUO7DLKTOUC/graph.json","events_json":"https://pith.science/api/pith-number/P7BB5MBILIM7HZGKUO7DLKTOUC/events.json","paper":"https://pith.science/paper/P7BB5MBI"},"agent_actions":{"view_html":"https://pith.science/pith/P7BB5MBILIM7HZGKUO7DLKTOUC","download_json":"https://pith.science/pith/P7BB5MBILIM7HZGKUO7DLKTOUC.json","view_paper":"https://pith.science/paper/P7BB5MBI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.12832&json=true","fetch_graph":"https://pith.science/api/pith-number/P7BB5MBILIM7HZGKUO7DLKTOUC/graph.json","fetch_events":"https://pith.science/api/pith-number/P7BB5MBILIM7HZGKUO7DLKTOUC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P7BB5MBILIM7HZGKUO7DLKTOUC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P7BB5MBILIM7HZGKUO7DLKTOUC/action/storage_attestation","attest_author":"https://pith.science/pith/P7BB5MBILIM7HZGKUO7DLKTOUC/action/author_attestation","sign_citation":"https://pith.science/pith/P7BB5MBILIM7HZGKUO7DLKTOUC/action/citation_signature","submit_replication":"https://pith.science/pith/P7BB5MBILIM7HZGKUO7DLKTOUC/action/replication_record"}},"created_at":"2026-05-17T23:39:48.188309+00:00","updated_at":"2026-05-17T23:39:48.188309+00:00"}