{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YI37BSGL4O7H36M55V45OK3FMG","short_pith_number":"pith:YI37BSGL","schema_version":"1.0","canonical_sha256":"c237f0c8cbe3be7df99ded79d72b6561972c4cbb241d36c1f08b533c44c7ef89","source":{"kind":"arxiv","id":"2607.26698","version":1},"attestation_state":"computed","paper":{"title":"MPEcho: A Melody and Phoneme-Aware Generative Framework for Controllable Cover Song Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chih-Pin Tan, Fang-Duo Tsai, Hsuan-Yu Yeh, Ting-Yi Hu, Wei-Jaw Lee, Yi-Hsuan Yang","submitted_at":"2026-07-29T09:45:13Z","abstract_excerpt":"Cover song generation (CSG) should preserve the melodic and linguistic content of a reference song while recreating the remaining musical components. The state-of-the-art model SongEcho utilizes $F_0$ sequences and voiced/unvoiced (V/UV) tags for conditioning; however, implicit linguistic information from V/UV tags cannot guarantee lyric accuracy, leading to a high phoneme error rate (PER). Inspired by singing voice synthesis (SVS), we propose MPEcho, which integrates a phoneme encoder and a length regulator (LR) into the SongEcho framework. By providing explicit phoneme-level conditioning and"},"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":"2607.26698","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-29T09:45:13Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"379d273e205fbaed9ceea3401539018d9d0096d4348babf1643ab50ba12c0c85","abstract_canon_sha256":"1f1b7434e6b1016e54503dfd0eeab413dfc22c84588f1ebab756ab1260abe158"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c237f0c8cbe3be7df99ded79d72b6561972c4cbb241d36c1f08b533c44c7ef89","last_reissued_at":"2026-07-30T01:21:58.218405Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:21:58.218405Z"},"graph_snapshot":{"paper":{"title":"MPEcho: A Melody and Phoneme-Aware Generative Framework for Controllable Cover Song Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chih-Pin Tan, Fang-Duo Tsai, Hsuan-Yu Yeh, Ting-Yi Hu, Wei-Jaw Lee, Yi-Hsuan Yang","submitted_at":"2026-07-29T09:45:13Z","abstract_excerpt":"Cover song generation (CSG) should preserve the melodic and linguistic content of a reference song while recreating the remaining musical components. The state-of-the-art model SongEcho utilizes $F_0$ sequences and voiced/unvoiced (V/UV) tags for conditioning; however, implicit linguistic information from V/UV tags cannot guarantee lyric accuracy, leading to a high phoneme error rate (PER). Inspired by singing voice synthesis (SVS), we propose MPEcho, which integrates a phoneme encoder and a length regulator (LR) into the SongEcho framework. By providing explicit phoneme-level conditioning and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26698","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/2607.26698/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":"2607.26698","created_at":"2026-07-30T01:21:58.223592+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.26698v1","created_at":"2026-07-30T01:21:58.223592+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26698","created_at":"2026-07-30T01:21:58.223592+00:00"},{"alias_kind":"pith_short_12","alias_value":"YI37BSGL4O7H","created_at":"2026-07-30T01:21:58.223592+00:00"},{"alias_kind":"pith_short_16","alias_value":"YI37BSGL4O7H36M5","created_at":"2026-07-30T01:21:58.223592+00:00"},{"alias_kind":"pith_short_8","alias_value":"YI37BSGL","created_at":"2026-07-30T01:21:58.223592+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/YI37BSGL4O7H36M55V45OK3FMG","json":"https://pith.science/pith/YI37BSGL4O7H36M55V45OK3FMG.json","graph_json":"https://pith.science/api/pith-number/YI37BSGL4O7H36M55V45OK3FMG/graph.json","events_json":"https://pith.science/api/pith-number/YI37BSGL4O7H36M55V45OK3FMG/events.json","paper":"https://pith.science/paper/YI37BSGL"},"agent_actions":{"view_html":"https://pith.science/pith/YI37BSGL4O7H36M55V45OK3FMG","download_json":"https://pith.science/pith/YI37BSGL4O7H36M55V45OK3FMG.json","view_paper":"https://pith.science/paper/YI37BSGL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.26698&json=true","fetch_graph":"https://pith.science/api/pith-number/YI37BSGL4O7H36M55V45OK3FMG/graph.json","fetch_events":"https://pith.science/api/pith-number/YI37BSGL4O7H36M55V45OK3FMG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YI37BSGL4O7H36M55V45OK3FMG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YI37BSGL4O7H36M55V45OK3FMG/action/storage_attestation","attest_author":"https://pith.science/pith/YI37BSGL4O7H36M55V45OK3FMG/action/author_attestation","sign_citation":"https://pith.science/pith/YI37BSGL4O7H36M55V45OK3FMG/action/citation_signature","submit_replication":"https://pith.science/pith/YI37BSGL4O7H36M55V45OK3FMG/action/replication_record"}},"created_at":"2026-07-30T01:21:58.223592+00:00","updated_at":"2026-07-30T01:21:58.223592+00:00"}