{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:32POXP24MAARBC3247M4NNLPIL","short_pith_number":"pith:32POXP24","schema_version":"1.0","canonical_sha256":"de9eebbf5c6001108b7ae7d9c6b56f42d6bd768d53404c123d74b5147241d014","source":{"kind":"arxiv","id":"1706.09559","version":1},"attestation_state":"computed","paper":{"title":"Audio Spectrogram Representations for Processing with Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.NE"],"primary_cat":"cs.SD","authors_text":"L. Wyse","submitted_at":"2017-06-29T03:04:06Z","abstract_excerpt":"One of the decisions that arise when designing a neural network for any application is how the data should be represented in order to be presented to, and possibly generated by, a neural network. For audio, the choice is less obvious than it seems to be for visual images, and a variety of representations have been used for different applications including the raw digitized sample stream, hand-crafted features, machine discovered features, MFCCs and variants that include deltas, and a variety of spectral representations. This paper reviews some of these representations and issues that arise, fo"},"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":"1706.09559","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-06-29T03:04:06Z","cross_cats_sorted":["cs.LG","cs.MM","cs.NE"],"title_canon_sha256":"68b2cd2e58a3bbaeb66b06c702cb92ada9c4a3e63e59bf004700369bfaf326ef","abstract_canon_sha256":"216a19db66b8929e1bbaa93b5e4847ec6dc384d013f4e8f6dc65312d865f7aae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:14.639465Z","signature_b64":"oE03irCsNJMOyr2t4ddnFS5z6EjiAA2toDywO2AJglrpdbU4uB6PJcmzSNFZrcmiThY+Nm73Gtgn0LzgzeKODg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de9eebbf5c6001108b7ae7d9c6b56f42d6bd768d53404c123d74b5147241d014","last_reissued_at":"2026-05-18T00:41:14.638784Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:14.638784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio Spectrogram Representations for Processing with Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.NE"],"primary_cat":"cs.SD","authors_text":"L. Wyse","submitted_at":"2017-06-29T03:04:06Z","abstract_excerpt":"One of the decisions that arise when designing a neural network for any application is how the data should be represented in order to be presented to, and possibly generated by, a neural network. For audio, the choice is less obvious than it seems to be for visual images, and a variety of representations have been used for different applications including the raw digitized sample stream, hand-crafted features, machine discovered features, MFCCs and variants that include deltas, and a variety of spectral representations. This paper reviews some of these representations and issues that arise, fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.09559","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":"1706.09559","created_at":"2026-05-18T00:41:14.638897+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.09559v1","created_at":"2026-05-18T00:41:14.638897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.09559","created_at":"2026-05-18T00:41:14.638897+00:00"},{"alias_kind":"pith_short_12","alias_value":"32POXP24MAAR","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_16","alias_value":"32POXP24MAARBC32","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_8","alias_value":"32POXP24","created_at":"2026-05-18T12:30:55.937587+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.06129","citing_title":"Towards Robust Voice Pathology Detection","ref_index":63,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/32POXP24MAARBC3247M4NNLPIL","json":"https://pith.science/pith/32POXP24MAARBC3247M4NNLPIL.json","graph_json":"https://pith.science/api/pith-number/32POXP24MAARBC3247M4NNLPIL/graph.json","events_json":"https://pith.science/api/pith-number/32POXP24MAARBC3247M4NNLPIL/events.json","paper":"https://pith.science/paper/32POXP24"},"agent_actions":{"view_html":"https://pith.science/pith/32POXP24MAARBC3247M4NNLPIL","download_json":"https://pith.science/pith/32POXP24MAARBC3247M4NNLPIL.json","view_paper":"https://pith.science/paper/32POXP24","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.09559&json=true","fetch_graph":"https://pith.science/api/pith-number/32POXP24MAARBC3247M4NNLPIL/graph.json","fetch_events":"https://pith.science/api/pith-number/32POXP24MAARBC3247M4NNLPIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/32POXP24MAARBC3247M4NNLPIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/32POXP24MAARBC3247M4NNLPIL/action/storage_attestation","attest_author":"https://pith.science/pith/32POXP24MAARBC3247M4NNLPIL/action/author_attestation","sign_citation":"https://pith.science/pith/32POXP24MAARBC3247M4NNLPIL/action/citation_signature","submit_replication":"https://pith.science/pith/32POXP24MAARBC3247M4NNLPIL/action/replication_record"}},"created_at":"2026-05-18T00:41:14.638897+00:00","updated_at":"2026-05-18T00:41:14.638897+00:00"}