{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AUHEEGLIYIMKSAAZVLKQB5MH55","short_pith_number":"pith:AUHEEGLI","schema_version":"1.0","canonical_sha256":"050e421968c218a90019aad500f587ef6552d85f86dfc49a0aa5031681beeea9","source":{"kind":"arxiv","id":"2308.16836","version":1},"attestation_state":"computed","paper":{"title":"Towards Improving the Expressiveness of Singing Voice Synthesis with BERT Derived Semantic Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Deyi Tuo, Helen Meng, Shaohuan Zhou, Shiyin Kang, Shun Lei, Weiya You, Yuren You, Zhiyong Wu","submitted_at":"2023-08-31T16:12:01Z","abstract_excerpt":"This paper presents an end-to-end high-quality singing voice synthesis (SVS) system that uses bidirectional encoder representation from Transformers (BERT) derived semantic embeddings to improve the expressiveness of the synthesized singing voice. Based on the main architecture of recently proposed VISinger, we put forward several specific designs for expressive singing voice synthesis. First, different from the previous SVS models, we use text representation of lyrics extracted from pre-trained BERT as additional input to the model. The representation contains information about semantics of t"},"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":"2308.16836","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-08-31T16:12:01Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"0d000da942f99138ffe8c9bc6367e4f583fe10034f964e8aaa7713ba2dd805cf","abstract_canon_sha256":"315ff5f4e6f3f97ab50620f44b0b655ce685cd5b17441a36da2923671bca8bbf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:39.985392Z","signature_b64":"z9M0xeiOrKRQlX0L/8hwlY6zYcn1tqru4FrFOmhkktumRa/DvGwZFmy/nTzd30diRI72WKzTKjwItUKyeddiBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"050e421968c218a90019aad500f587ef6552d85f86dfc49a0aa5031681beeea9","last_reissued_at":"2026-07-05T06:46:39.984926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:39.984926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Improving the Expressiveness of Singing Voice Synthesis with BERT Derived Semantic Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Deyi Tuo, Helen Meng, Shaohuan Zhou, Shiyin Kang, Shun Lei, Weiya You, Yuren You, Zhiyong Wu","submitted_at":"2023-08-31T16:12:01Z","abstract_excerpt":"This paper presents an end-to-end high-quality singing voice synthesis (SVS) system that uses bidirectional encoder representation from Transformers (BERT) derived semantic embeddings to improve the expressiveness of the synthesized singing voice. Based on the main architecture of recently proposed VISinger, we put forward several specific designs for expressive singing voice synthesis. First, different from the previous SVS models, we use text representation of lyrics extracted from pre-trained BERT as additional input to the model. The representation contains information about semantics of t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.16836","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/2308.16836/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":"2308.16836","created_at":"2026-07-05T06:46:39.984998+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.16836v1","created_at":"2026-07-05T06:46:39.984998+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.16836","created_at":"2026-07-05T06:46:39.984998+00:00"},{"alias_kind":"pith_short_12","alias_value":"AUHEEGLIYIMK","created_at":"2026-07-05T06:46:39.984998+00:00"},{"alias_kind":"pith_short_16","alias_value":"AUHEEGLIYIMKSAAZ","created_at":"2026-07-05T06:46:39.984998+00:00"},{"alias_kind":"pith_short_8","alias_value":"AUHEEGLI","created_at":"2026-07-05T06:46:39.984998+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/AUHEEGLIYIMKSAAZVLKQB5MH55","json":"https://pith.science/pith/AUHEEGLIYIMKSAAZVLKQB5MH55.json","graph_json":"https://pith.science/api/pith-number/AUHEEGLIYIMKSAAZVLKQB5MH55/graph.json","events_json":"https://pith.science/api/pith-number/AUHEEGLIYIMKSAAZVLKQB5MH55/events.json","paper":"https://pith.science/paper/AUHEEGLI"},"agent_actions":{"view_html":"https://pith.science/pith/AUHEEGLIYIMKSAAZVLKQB5MH55","download_json":"https://pith.science/pith/AUHEEGLIYIMKSAAZVLKQB5MH55.json","view_paper":"https://pith.science/paper/AUHEEGLI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.16836&json=true","fetch_graph":"https://pith.science/api/pith-number/AUHEEGLIYIMKSAAZVLKQB5MH55/graph.json","fetch_events":"https://pith.science/api/pith-number/AUHEEGLIYIMKSAAZVLKQB5MH55/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AUHEEGLIYIMKSAAZVLKQB5MH55/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AUHEEGLIYIMKSAAZVLKQB5MH55/action/storage_attestation","attest_author":"https://pith.science/pith/AUHEEGLIYIMKSAAZVLKQB5MH55/action/author_attestation","sign_citation":"https://pith.science/pith/AUHEEGLIYIMKSAAZVLKQB5MH55/action/citation_signature","submit_replication":"https://pith.science/pith/AUHEEGLIYIMKSAAZVLKQB5MH55/action/replication_record"}},"created_at":"2026-07-05T06:46:39.984998+00:00","updated_at":"2026-07-05T06:46:39.984998+00:00"}