{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ROE4Z62M2JB3MZH5CXP73NZMFW","short_pith_number":"pith:ROE4Z62M","schema_version":"1.0","canonical_sha256":"8b89ccfb4cd243b664fd15dffdb72c2d9e9804adb93e8257eec79cad9731d066","source":{"kind":"arxiv","id":"2407.02049","version":1},"attestation_state":"computed","paper":{"title":"Accompanied Singing Voice Synthesis with Fully Text-controlled Melody","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Lichao Zhang, Rongjie Huang, Ruiqi Li, Siqi Zheng, Yongqi Wang, Zhiqing Hong, Zhou Zhao","submitted_at":"2024-07-02T08:23:38Z","abstract_excerpt":"Text-to-song (TTSong) is a music generation task that synthesizes accompanied singing voices. Current TTSong methods, inherited from singing voice synthesis (SVS), require melody-related information that can sometimes be impractical, such as music scores or MIDI sequences. We present MelodyLM, the first TTSong model that generates high-quality song pieces with fully text-controlled melodies, achieving minimal user requirements and maximum control flexibility. MelodyLM explicitly models MIDI as the intermediate melody-related feature and sequentially generates vocal tracks in a language model m"},"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":"2407.02049","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-02T08:23:38Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"563e1a7ac743b35564b8bd61680c8e2a73ed8fd8b80d65f44398c0b5a5572cd1","abstract_canon_sha256":"7ede3a0104cd812d5457518abcfb390f8b80be4136c444fd301727f5cb7e7951"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:09.192348Z","signature_b64":"kxs38VpdzmUoJGx3/28kgX0wOoakSDI6NUvOlsJ5bcxwfwEGGu1jWcqLFU3KFRLdBPwm8weq4s4f0f7D12kjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b89ccfb4cd243b664fd15dffdb72c2d9e9804adb93e8257eec79cad9731d066","last_reissued_at":"2026-07-05T08:39:09.191817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:09.191817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accompanied Singing Voice Synthesis with Fully Text-controlled Melody","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Lichao Zhang, Rongjie Huang, Ruiqi Li, Siqi Zheng, Yongqi Wang, Zhiqing Hong, Zhou Zhao","submitted_at":"2024-07-02T08:23:38Z","abstract_excerpt":"Text-to-song (TTSong) is a music generation task that synthesizes accompanied singing voices. Current TTSong methods, inherited from singing voice synthesis (SVS), require melody-related information that can sometimes be impractical, such as music scores or MIDI sequences. We present MelodyLM, the first TTSong model that generates high-quality song pieces with fully text-controlled melodies, achieving minimal user requirements and maximum control flexibility. MelodyLM explicitly models MIDI as the intermediate melody-related feature and sequentially generates vocal tracks in a language model m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02049","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/2407.02049/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":"2407.02049","created_at":"2026-07-05T08:39:09.191880+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.02049v1","created_at":"2026-07-05T08:39:09.191880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02049","created_at":"2026-07-05T08:39:09.191880+00:00"},{"alias_kind":"pith_short_12","alias_value":"ROE4Z62M2JB3","created_at":"2026-07-05T08:39:09.191880+00:00"},{"alias_kind":"pith_short_16","alias_value":"ROE4Z62M2JB3MZH5","created_at":"2026-07-05T08:39:09.191880+00:00"},{"alias_kind":"pith_short_8","alias_value":"ROE4Z62M","created_at":"2026-07-05T08:39:09.191880+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01677","citing_title":"UniVocal: Unified Speech-Singing Code-Switching Synthesis","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30642","citing_title":"LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Training","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2602.22029","citing_title":"MIDI-Informed Singing Accompaniment Generation in a Compositional Song Pipeline","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ROE4Z62M2JB3MZH5CXP73NZMFW","json":"https://pith.science/pith/ROE4Z62M2JB3MZH5CXP73NZMFW.json","graph_json":"https://pith.science/api/pith-number/ROE4Z62M2JB3MZH5CXP73NZMFW/graph.json","events_json":"https://pith.science/api/pith-number/ROE4Z62M2JB3MZH5CXP73NZMFW/events.json","paper":"https://pith.science/paper/ROE4Z62M"},"agent_actions":{"view_html":"https://pith.science/pith/ROE4Z62M2JB3MZH5CXP73NZMFW","download_json":"https://pith.science/pith/ROE4Z62M2JB3MZH5CXP73NZMFW.json","view_paper":"https://pith.science/paper/ROE4Z62M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.02049&json=true","fetch_graph":"https://pith.science/api/pith-number/ROE4Z62M2JB3MZH5CXP73NZMFW/graph.json","fetch_events":"https://pith.science/api/pith-number/ROE4Z62M2JB3MZH5CXP73NZMFW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ROE4Z62M2JB3MZH5CXP73NZMFW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ROE4Z62M2JB3MZH5CXP73NZMFW/action/storage_attestation","attest_author":"https://pith.science/pith/ROE4Z62M2JB3MZH5CXP73NZMFW/action/author_attestation","sign_citation":"https://pith.science/pith/ROE4Z62M2JB3MZH5CXP73NZMFW/action/citation_signature","submit_replication":"https://pith.science/pith/ROE4Z62M2JB3MZH5CXP73NZMFW/action/replication_record"}},"created_at":"2026-07-05T08:39:09.191880+00:00","updated_at":"2026-07-05T08:39:09.191880+00:00"}