{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:IKWAYGRLOLDZHGPKPS7MMFI6BJ","short_pith_number":"pith:IKWAYGRL","schema_version":"1.0","canonical_sha256":"42ac0c1a2b72c79399ea7cbec6151e0a5d10ab6e2a5bb0e689008b98b6e2bd00","source":{"kind":"arxiv","id":"1712.00254","version":1},"attestation_state":"computed","paper":{"title":"Utilizing Domain Knowledge in End-to-End Audio Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"Hendrik Purwins, Jose Luis Diez Antich, Lars Maal{\\o}e, Tycho Max Sylvester Tax","submitted_at":"2017-12-01T09:49:21Z","abstract_excerpt":"End-to-end neural network based approaches to audio modelling are generally outperformed by models trained on high-level data representations. In this paper we present preliminary work that shows the feasibility of training the first layers of a deep convolutional neural network (CNN) model to learn the commonly-used log-scaled mel-spectrogram transformation. Secondly, we demonstrate that upon initializing the first layers of an end-to-end CNN classifier with the learned transformation, convergence and performance on the ESC-50 environmental sound classification dataset are similar to a CNN-ba"},"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":"1712.00254","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-12-01T09:49:21Z","cross_cats_sorted":["eess.AS","stat.ML"],"title_canon_sha256":"c63f5c02fc5b2751a4a5ea34085e4d027a373835430332fcf09d02ba7b68fb4b","abstract_canon_sha256":"e4c63107a7ccfaaf34ebc9912e2544d570bc00c9f26990117dd9abc3b149e0a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:06.746825Z","signature_b64":"5AfO0q1KRKJwGrtuDrCX5zeswdF5hmiahxZGY/Atp0r6QOZllHfBnNOBB3J8PjyQdWh6Uxo97xzpQ7uX/aB6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42ac0c1a2b72c79399ea7cbec6151e0a5d10ab6e2a5bb0e689008b98b6e2bd00","last_reissued_at":"2026-05-18T00:29:06.746232Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:06.746232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Utilizing Domain Knowledge in End-to-End Audio Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"Hendrik Purwins, Jose Luis Diez Antich, Lars Maal{\\o}e, Tycho Max Sylvester Tax","submitted_at":"2017-12-01T09:49:21Z","abstract_excerpt":"End-to-end neural network based approaches to audio modelling are generally outperformed by models trained on high-level data representations. In this paper we present preliminary work that shows the feasibility of training the first layers of a deep convolutional neural network (CNN) model to learn the commonly-used log-scaled mel-spectrogram transformation. Secondly, we demonstrate that upon initializing the first layers of an end-to-end CNN classifier with the learned transformation, convergence and performance on the ESC-50 environmental sound classification dataset are similar to a CNN-ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.00254","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":"1712.00254","created_at":"2026-05-18T00:29:06.746328+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.00254v1","created_at":"2026-05-18T00:29:06.746328+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.00254","created_at":"2026-05-18T00:29:06.746328+00:00"},{"alias_kind":"pith_short_12","alias_value":"IKWAYGRLOLDZ","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"IKWAYGRLOLDZHGPK","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"IKWAYGRL","created_at":"2026-05-18T12:31:21.493067+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/IKWAYGRLOLDZHGPKPS7MMFI6BJ","json":"https://pith.science/pith/IKWAYGRLOLDZHGPKPS7MMFI6BJ.json","graph_json":"https://pith.science/api/pith-number/IKWAYGRLOLDZHGPKPS7MMFI6BJ/graph.json","events_json":"https://pith.science/api/pith-number/IKWAYGRLOLDZHGPKPS7MMFI6BJ/events.json","paper":"https://pith.science/paper/IKWAYGRL"},"agent_actions":{"view_html":"https://pith.science/pith/IKWAYGRLOLDZHGPKPS7MMFI6BJ","download_json":"https://pith.science/pith/IKWAYGRLOLDZHGPKPS7MMFI6BJ.json","view_paper":"https://pith.science/paper/IKWAYGRL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.00254&json=true","fetch_graph":"https://pith.science/api/pith-number/IKWAYGRLOLDZHGPKPS7MMFI6BJ/graph.json","fetch_events":"https://pith.science/api/pith-number/IKWAYGRLOLDZHGPKPS7MMFI6BJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IKWAYGRLOLDZHGPKPS7MMFI6BJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IKWAYGRLOLDZHGPKPS7MMFI6BJ/action/storage_attestation","attest_author":"https://pith.science/pith/IKWAYGRLOLDZHGPKPS7MMFI6BJ/action/author_attestation","sign_citation":"https://pith.science/pith/IKWAYGRLOLDZHGPKPS7MMFI6BJ/action/citation_signature","submit_replication":"https://pith.science/pith/IKWAYGRLOLDZHGPKPS7MMFI6BJ/action/replication_record"}},"created_at":"2026-05-18T00:29:06.746328+00:00","updated_at":"2026-05-18T00:29:06.746328+00:00"}