{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XMN4YCUBROLMGUERYZRNXPAXKS","short_pith_number":"pith:XMN4YCUB","schema_version":"1.0","canonical_sha256":"bb1bcc0a818b96c35091c662dbbc1754b6ef7c8060bbbdcec58fb4bb2e11f09e","source":{"kind":"arxiv","id":"2306.10785","version":1},"attestation_state":"computed","paper":{"title":"Multitrack Music Transcription with a Time-Frequency Perceiver","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ju-Chiang Wang, Wei-Tsung Lu, Yun-Ning Hung","submitted_at":"2023-06-19T08:58:26Z","abstract_excerpt":"Multitrack music transcription aims to transcribe a music audio input into the musical notes of multiple instruments simultaneously. It is a very challenging task that typically requires a more complex model to achieve satisfactory result. In addition, prior works mostly focus on transcriptions of regular instruments, however, neglecting vocals, which are usually the most important signal source if present in a piece of music. In this paper, we propose a novel deep neural network architecture, Perceiver TF, to model the time-frequency representation of audio input for multitrack transcription."},"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":"2306.10785","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-06-19T08:58:26Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"c4ee0750416e67fbb412503563ec8c1837329b2207a265abe04d388334ed48a4","abstract_canon_sha256":"54b0c72db088972b16ffb932d7259183b1c618630476eb1341a7594f1ed024a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:22:11.733799Z","signature_b64":"5HspEoVP3SsvrAc0zqQqFn2ig9YpNlNMsrFevaX5EhYwXd6sYt9jCINYPQU1A/r/EZ5uUvVRdOeGDqB+gusTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb1bcc0a818b96c35091c662dbbc1754b6ef7c8060bbbdcec58fb4bb2e11f09e","last_reissued_at":"2026-07-05T06:22:11.733291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:22:11.733291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multitrack Music Transcription with a Time-Frequency Perceiver","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ju-Chiang Wang, Wei-Tsung Lu, Yun-Ning Hung","submitted_at":"2023-06-19T08:58:26Z","abstract_excerpt":"Multitrack music transcription aims to transcribe a music audio input into the musical notes of multiple instruments simultaneously. It is a very challenging task that typically requires a more complex model to achieve satisfactory result. In addition, prior works mostly focus on transcriptions of regular instruments, however, neglecting vocals, which are usually the most important signal source if present in a piece of music. In this paper, we propose a novel deep neural network architecture, Perceiver TF, to model the time-frequency representation of audio input for multitrack transcription."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10785","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/2306.10785/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":"2306.10785","created_at":"2026-07-05T06:22:11.733364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.10785v1","created_at":"2026-07-05T06:22:11.733364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10785","created_at":"2026-07-05T06:22:11.733364+00:00"},{"alias_kind":"pith_short_12","alias_value":"XMN4YCUBROLM","created_at":"2026-07-05T06:22:11.733364+00:00"},{"alias_kind":"pith_short_16","alias_value":"XMN4YCUBROLMGUER","created_at":"2026-07-05T06:22:11.733364+00:00"},{"alias_kind":"pith_short_8","alias_value":"XMN4YCUB","created_at":"2026-07-05T06:22:11.733364+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/XMN4YCUBROLMGUERYZRNXPAXKS","json":"https://pith.science/pith/XMN4YCUBROLMGUERYZRNXPAXKS.json","graph_json":"https://pith.science/api/pith-number/XMN4YCUBROLMGUERYZRNXPAXKS/graph.json","events_json":"https://pith.science/api/pith-number/XMN4YCUBROLMGUERYZRNXPAXKS/events.json","paper":"https://pith.science/paper/XMN4YCUB"},"agent_actions":{"view_html":"https://pith.science/pith/XMN4YCUBROLMGUERYZRNXPAXKS","download_json":"https://pith.science/pith/XMN4YCUBROLMGUERYZRNXPAXKS.json","view_paper":"https://pith.science/paper/XMN4YCUB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.10785&json=true","fetch_graph":"https://pith.science/api/pith-number/XMN4YCUBROLMGUERYZRNXPAXKS/graph.json","fetch_events":"https://pith.science/api/pith-number/XMN4YCUBROLMGUERYZRNXPAXKS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XMN4YCUBROLMGUERYZRNXPAXKS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XMN4YCUBROLMGUERYZRNXPAXKS/action/storage_attestation","attest_author":"https://pith.science/pith/XMN4YCUBROLMGUERYZRNXPAXKS/action/author_attestation","sign_citation":"https://pith.science/pith/XMN4YCUBROLMGUERYZRNXPAXKS/action/citation_signature","submit_replication":"https://pith.science/pith/XMN4YCUBROLMGUERYZRNXPAXKS/action/replication_record"}},"created_at":"2026-07-05T06:22:11.733364+00:00","updated_at":"2026-07-05T06:22:11.733364+00:00"}