{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2SDCNSOKQCDRRNONDKJABBGOMV","short_pith_number":"pith:2SDCNSOK","schema_version":"1.0","canonical_sha256":"d48626c9ca808718b5cd1a920084ce65670968daa183c4eff7f6bb69b5b6fef3","source":{"kind":"arxiv","id":"2212.06397","version":1},"attestation_state":"computed","paper":{"title":"Style-Label-Free: Cross-Speaker Style Transfer by Quantized VAE and Speaker-wise Normalization in Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chunyu Qiang, Hao Che, Peng Yang, Xiaorui Wang, Zhongyuan Wang","submitted_at":"2022-12-13T06:26:25Z","abstract_excerpt":"Cross-speaker style transfer in speech synthesis aims at transferring a style from source speaker to synthesised speech of a target speaker's timbre. Most previous approaches rely on data with style labels, but manually-annotated labels are expensive and not always reliable. In response to this problem, we propose Style-Label-Free, a cross-speaker style transfer method, which can realize the style transfer from source speaker to target speaker without style labels. Firstly, a reference encoder structure based on quantized variational autoencoder (Q-VAE) and style bottleneck is designed to extr"},"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":"2212.06397","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-12-13T06:26:25Z","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"title_canon_sha256":"13828222a6b5bc1f0c8ffbbb90fa92627f71860add1402e9d83abe5b6e1cd788","abstract_canon_sha256":"e811933490825b1d70484815285e62f84f66e11b99303d8caf1abcfbfac2a2af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:24:49.816724Z","signature_b64":"YIHs1CyhB8n9GZOkPFTUQSIFSp8P0NvOmdAhaXZU+pg8qLktGX6q3GmikVhR4z8oTTHH5JHEUcKMBj3C2bShDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d48626c9ca808718b5cd1a920084ce65670968daa183c4eff7f6bb69b5b6fef3","last_reissued_at":"2026-07-05T05:24:49.816324Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:24:49.816324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Style-Label-Free: Cross-Speaker Style Transfer by Quantized VAE and Speaker-wise Normalization in Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chunyu Qiang, Hao Che, Peng Yang, Xiaorui Wang, Zhongyuan Wang","submitted_at":"2022-12-13T06:26:25Z","abstract_excerpt":"Cross-speaker style transfer in speech synthesis aims at transferring a style from source speaker to synthesised speech of a target speaker's timbre. Most previous approaches rely on data with style labels, but manually-annotated labels are expensive and not always reliable. In response to this problem, we propose Style-Label-Free, a cross-speaker style transfer method, which can realize the style transfer from source speaker to target speaker without style labels. Firstly, a reference encoder structure based on quantized variational autoencoder (Q-VAE) and style bottleneck is designed to extr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.06397","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/2212.06397/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":"2212.06397","created_at":"2026-07-05T05:24:49.816382+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.06397v1","created_at":"2026-07-05T05:24:49.816382+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.06397","created_at":"2026-07-05T05:24:49.816382+00:00"},{"alias_kind":"pith_short_12","alias_value":"2SDCNSOKQCDR","created_at":"2026-07-05T05:24:49.816382+00:00"},{"alias_kind":"pith_short_16","alias_value":"2SDCNSOKQCDRRNON","created_at":"2026-07-05T05:24:49.816382+00:00"},{"alias_kind":"pith_short_8","alias_value":"2SDCNSOK","created_at":"2026-07-05T05:24:49.816382+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/2SDCNSOKQCDRRNONDKJABBGOMV","json":"https://pith.science/pith/2SDCNSOKQCDRRNONDKJABBGOMV.json","graph_json":"https://pith.science/api/pith-number/2SDCNSOKQCDRRNONDKJABBGOMV/graph.json","events_json":"https://pith.science/api/pith-number/2SDCNSOKQCDRRNONDKJABBGOMV/events.json","paper":"https://pith.science/paper/2SDCNSOK"},"agent_actions":{"view_html":"https://pith.science/pith/2SDCNSOKQCDRRNONDKJABBGOMV","download_json":"https://pith.science/pith/2SDCNSOKQCDRRNONDKJABBGOMV.json","view_paper":"https://pith.science/paper/2SDCNSOK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.06397&json=true","fetch_graph":"https://pith.science/api/pith-number/2SDCNSOKQCDRRNONDKJABBGOMV/graph.json","fetch_events":"https://pith.science/api/pith-number/2SDCNSOKQCDRRNONDKJABBGOMV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2SDCNSOKQCDRRNONDKJABBGOMV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2SDCNSOKQCDRRNONDKJABBGOMV/action/storage_attestation","attest_author":"https://pith.science/pith/2SDCNSOKQCDRRNONDKJABBGOMV/action/author_attestation","sign_citation":"https://pith.science/pith/2SDCNSOKQCDRRNONDKJABBGOMV/action/citation_signature","submit_replication":"https://pith.science/pith/2SDCNSOKQCDRRNONDKJABBGOMV/action/replication_record"}},"created_at":"2026-07-05T05:24:49.816382+00:00","updated_at":"2026-07-05T05:24:49.816382+00:00"}