{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CHS4QWMBPEWYBLF3S2EPZZCADQ","short_pith_number":"pith:CHS4QWMB","schema_version":"1.0","canonical_sha256":"11e5c85981792d80acbb9688fce4401c2143e1e3eabff6c037b5d8b7d25df906","source":{"kind":"arxiv","id":"2206.12230","version":1},"attestation_state":"computed","paper":{"title":"Deformable CNN and Imbalance-Aware Feature Learning for Singing Technique Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hiroko Terasawa, Juhan Nam, Yuya Yamamoto","submitted_at":"2022-06-24T11:56:51Z","abstract_excerpt":"Singing techniques are used for expressive vocal performances by employing temporal fluctuations of the timbre, the pitch, and other components of the voice. Their classification is a challenging task, because of mainly two factors: 1) the fluctuations in singing techniques have a wide variety and are affected by many factors and 2) existing datasets are imbalanced. To deal with these problems, we developed a novel audio feature learning method based on deformable convolution with decoupled training of the feature extractor and the classifier using a class-weighted loss function. The experimen"},"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":"2206.12230","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-06-24T11:56:51Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"bdf726c74247bdc0aff848e3978333667bc1a30661151dabe59b6cdfaf056162","abstract_canon_sha256":"1a02c6669e182036257faf24b3f547cf000773c1359c4a6d7c2693639188478c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:34:34.291285Z","signature_b64":"QmOYLmHr/ocVGaGc2Hptt1V131M/eXxrd201WbyK7vis5OlBMgsPYADq8vLq6w/aMP0MMhlxDf85vDHQyU/UBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11e5c85981792d80acbb9688fce4401c2143e1e3eabff6c037b5d8b7d25df906","last_reissued_at":"2026-07-05T04:34:34.290863Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:34:34.290863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deformable CNN and Imbalance-Aware Feature Learning for Singing Technique Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hiroko Terasawa, Juhan Nam, Yuya Yamamoto","submitted_at":"2022-06-24T11:56:51Z","abstract_excerpt":"Singing techniques are used for expressive vocal performances by employing temporal fluctuations of the timbre, the pitch, and other components of the voice. Their classification is a challenging task, because of mainly two factors: 1) the fluctuations in singing techniques have a wide variety and are affected by many factors and 2) existing datasets are imbalanced. To deal with these problems, we developed a novel audio feature learning method based on deformable convolution with decoupled training of the feature extractor and the classifier using a class-weighted loss function. The experimen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.12230","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.12230/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":"2206.12230","created_at":"2026-07-05T04:34:34.290923+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.12230v1","created_at":"2026-07-05T04:34:34.290923+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.12230","created_at":"2026-07-05T04:34:34.290923+00:00"},{"alias_kind":"pith_short_12","alias_value":"CHS4QWMBPEWY","created_at":"2026-07-05T04:34:34.290923+00:00"},{"alias_kind":"pith_short_16","alias_value":"CHS4QWMBPEWYBLF3","created_at":"2026-07-05T04:34:34.290923+00:00"},{"alias_kind":"pith_short_8","alias_value":"CHS4QWMB","created_at":"2026-07-05T04:34:34.290923+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.01108","citing_title":"MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CHS4QWMBPEWYBLF3S2EPZZCADQ","json":"https://pith.science/pith/CHS4QWMBPEWYBLF3S2EPZZCADQ.json","graph_json":"https://pith.science/api/pith-number/CHS4QWMBPEWYBLF3S2EPZZCADQ/graph.json","events_json":"https://pith.science/api/pith-number/CHS4QWMBPEWYBLF3S2EPZZCADQ/events.json","paper":"https://pith.science/paper/CHS4QWMB"},"agent_actions":{"view_html":"https://pith.science/pith/CHS4QWMBPEWYBLF3S2EPZZCADQ","download_json":"https://pith.science/pith/CHS4QWMBPEWYBLF3S2EPZZCADQ.json","view_paper":"https://pith.science/paper/CHS4QWMB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.12230&json=true","fetch_graph":"https://pith.science/api/pith-number/CHS4QWMBPEWYBLF3S2EPZZCADQ/graph.json","fetch_events":"https://pith.science/api/pith-number/CHS4QWMBPEWYBLF3S2EPZZCADQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CHS4QWMBPEWYBLF3S2EPZZCADQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CHS4QWMBPEWYBLF3S2EPZZCADQ/action/storage_attestation","attest_author":"https://pith.science/pith/CHS4QWMBPEWYBLF3S2EPZZCADQ/action/author_attestation","sign_citation":"https://pith.science/pith/CHS4QWMBPEWYBLF3S2EPZZCADQ/action/citation_signature","submit_replication":"https://pith.science/pith/CHS4QWMBPEWYBLF3S2EPZZCADQ/action/replication_record"}},"created_at":"2026-07-05T04:34:34.290923+00:00","updated_at":"2026-07-05T04:34:34.290923+00:00"}