{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7GDNARYKKXKRV3P7RT2RSZRU7N","short_pith_number":"pith:7GDNARYK","schema_version":"1.0","canonical_sha256":"f986d0470a55d51aedff8cf5196634fb5fcdd2fea95e01b3491daaff38bf38b3","source":{"kind":"arxiv","id":"2301.12258","version":3},"attestation_state":"computed","paper":{"title":"Cross-domain Neural Pitch and Periodicity Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bryan Pardo, Caedon Hsieh, Max Morrison, Nathan Pruyne","submitted_at":"2023-01-28T17:30:47Z","abstract_excerpt":"Pitch is a foundational aspect of our perception of audio signals. Pitch contours are commonly used to analyze speech and music signals and as input features for many audio tasks, including music transcription, singing voice synthesis, and prosody editing. In this paper, we describe a set of techniques for improving the accuracy of widely-used neural pitch and periodicity estimators to achieve state-of-the-art performance on both speech and music. We also introduce a novel entropy-based method for extracting periodicity and per-frame voiced-unvoiced classifications from statistical inference-b"},"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":"2301.12258","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-01-28T17:30:47Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"afafc3953e893d57d13b9300f8416becc9e31aa690b533dce591fba77ac2ca96","abstract_canon_sha256":"d13317920378c7fd4dfa5cafdc41d7694451fee86bc2faf5a4f0127757acbed9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:01.121012Z","signature_b64":"FQV3BFlRwNjKMI7PXzCdDNt0mgpZZI4XN9IIUd5NJBDfr5HupU1Zj9Dfic7+tJq4YBeuw+soprPf5ItWslDcCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f986d0470a55d51aedff8cf5196634fb5fcdd2fea95e01b3491daaff38bf38b3","last_reissued_at":"2026-07-05T08:54:01.120585Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:01.120585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-domain Neural Pitch and Periodicity Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bryan Pardo, Caedon Hsieh, Max Morrison, Nathan Pruyne","submitted_at":"2023-01-28T17:30:47Z","abstract_excerpt":"Pitch is a foundational aspect of our perception of audio signals. Pitch contours are commonly used to analyze speech and music signals and as input features for many audio tasks, including music transcription, singing voice synthesis, and prosody editing. In this paper, we describe a set of techniques for improving the accuracy of widely-used neural pitch and periodicity estimators to achieve state-of-the-art performance on both speech and music. We also introduce a novel entropy-based method for extracting periodicity and per-frame voiced-unvoiced classifications from statistical inference-b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12258","kind":"arxiv","version":3},"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/2301.12258/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":"2301.12258","created_at":"2026-07-05T08:54:01.120645+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.12258v3","created_at":"2026-07-05T08:54:01.120645+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12258","created_at":"2026-07-05T08:54:01.120645+00:00"},{"alias_kind":"pith_short_12","alias_value":"7GDNARYKKXKR","created_at":"2026-07-05T08:54:01.120645+00:00"},{"alias_kind":"pith_short_16","alias_value":"7GDNARYKKXKRV3P7","created_at":"2026-07-05T08:54:01.120645+00:00"},{"alias_kind":"pith_short_8","alias_value":"7GDNARYK","created_at":"2026-07-05T08:54:01.120645+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.15322","citing_title":"Acoustic and Facial Markers of Perceived Conversational Success in Spontaneous Speech","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7GDNARYKKXKRV3P7RT2RSZRU7N","json":"https://pith.science/pith/7GDNARYKKXKRV3P7RT2RSZRU7N.json","graph_json":"https://pith.science/api/pith-number/7GDNARYKKXKRV3P7RT2RSZRU7N/graph.json","events_json":"https://pith.science/api/pith-number/7GDNARYKKXKRV3P7RT2RSZRU7N/events.json","paper":"https://pith.science/paper/7GDNARYK"},"agent_actions":{"view_html":"https://pith.science/pith/7GDNARYKKXKRV3P7RT2RSZRU7N","download_json":"https://pith.science/pith/7GDNARYKKXKRV3P7RT2RSZRU7N.json","view_paper":"https://pith.science/paper/7GDNARYK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.12258&json=true","fetch_graph":"https://pith.science/api/pith-number/7GDNARYKKXKRV3P7RT2RSZRU7N/graph.json","fetch_events":"https://pith.science/api/pith-number/7GDNARYKKXKRV3P7RT2RSZRU7N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7GDNARYKKXKRV3P7RT2RSZRU7N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7GDNARYKKXKRV3P7RT2RSZRU7N/action/storage_attestation","attest_author":"https://pith.science/pith/7GDNARYKKXKRV3P7RT2RSZRU7N/action/author_attestation","sign_citation":"https://pith.science/pith/7GDNARYKKXKRV3P7RT2RSZRU7N/action/citation_signature","submit_replication":"https://pith.science/pith/7GDNARYKKXKRV3P7RT2RSZRU7N/action/replication_record"}},"created_at":"2026-07-05T08:54:01.120645+00:00","updated_at":"2026-07-05T08:54:01.120645+00:00"}