{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ODAWM5ZWDBK3GXE7MDHKUQZXOK","short_pith_number":"pith:ODAWM5ZW","schema_version":"1.0","canonical_sha256":"70c16677361855b35c9f60ceaa4337729e2b1784f6524ddb18e3980cf751cbc5","source":{"kind":"arxiv","id":"2311.12454","version":2},"attestation_state":"computed","paper":{"title":"HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech Synthesis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ha-Yeong Choi, Sang-Hoon Lee, Seong-Whan Lee, Seung-Bin Kim","submitted_at":"2023-11-21T09:07:11Z","abstract_excerpt":"Large language models (LLM)-based speech synthesis has been widely adopted in zero-shot speech synthesis. However, they require a large-scale data and possess the same limitations as previous autoregressive speech models, including slow inference speed and lack of robustness. This paper proposes HierSpeech++, a fast and strong zero-shot speech synthesizer for text-to-speech (TTS) and voice conversion (VC). We verified that hierarchical speech synthesis frameworks could significantly improve the robustness and expressiveness of the synthetic speech. Furthermore, we significantly improve the nat"},"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":"2311.12454","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-11-21T09:07:11Z","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"title_canon_sha256":"0b90cf44c6cf84d5f27a66665f829d99b7f0d44d008e6dc1c916b46f154d52e8","abstract_canon_sha256":"15fcf3eae500e3c002227e5308df0054098eed8202473cb1ea2bb3133b0c5c81"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:50.674078Z","signature_b64":"z2tkSgVpaIf6AlZ+6KN7rUYuuvFDlTYelUk8iUIfZ10zY0EMrhoklpAVjNyLyDqyb5qPqAk9OZeqp95r0JWEDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70c16677361855b35c9f60ceaa4337729e2b1784f6524ddb18e3980cf751cbc5","last_reissued_at":"2026-07-05T07:16:50.673624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:50.673624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech Synthesis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ha-Yeong Choi, Sang-Hoon Lee, Seong-Whan Lee, Seung-Bin Kim","submitted_at":"2023-11-21T09:07:11Z","abstract_excerpt":"Large language models (LLM)-based speech synthesis has been widely adopted in zero-shot speech synthesis. However, they require a large-scale data and possess the same limitations as previous autoregressive speech models, including slow inference speed and lack of robustness. This paper proposes HierSpeech++, a fast and strong zero-shot speech synthesizer for text-to-speech (TTS) and voice conversion (VC). We verified that hierarchical speech synthesis frameworks could significantly improve the robustness and expressiveness of the synthetic speech. Furthermore, we significantly improve the nat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.12454","kind":"arxiv","version":2},"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/2311.12454/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":"2311.12454","created_at":"2026-07-05T07:16:50.673682+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.12454v2","created_at":"2026-07-05T07:16:50.673682+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12454","created_at":"2026-07-05T07:16:50.673682+00:00"},{"alias_kind":"pith_short_12","alias_value":"ODAWM5ZWDBK3","created_at":"2026-07-05T07:16:50.673682+00:00"},{"alias_kind":"pith_short_16","alias_value":"ODAWM5ZWDBK3GXE7","created_at":"2026-07-05T07:16:50.673682+00:00"},{"alias_kind":"pith_short_8","alias_value":"ODAWM5ZW","created_at":"2026-07-05T07:16:50.673682+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.02430","citing_title":"Seed-TTS: A Family of High-Quality Versatile Speech Generation Models","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ODAWM5ZWDBK3GXE7MDHKUQZXOK","json":"https://pith.science/pith/ODAWM5ZWDBK3GXE7MDHKUQZXOK.json","graph_json":"https://pith.science/api/pith-number/ODAWM5ZWDBK3GXE7MDHKUQZXOK/graph.json","events_json":"https://pith.science/api/pith-number/ODAWM5ZWDBK3GXE7MDHKUQZXOK/events.json","paper":"https://pith.science/paper/ODAWM5ZW"},"agent_actions":{"view_html":"https://pith.science/pith/ODAWM5ZWDBK3GXE7MDHKUQZXOK","download_json":"https://pith.science/pith/ODAWM5ZWDBK3GXE7MDHKUQZXOK.json","view_paper":"https://pith.science/paper/ODAWM5ZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.12454&json=true","fetch_graph":"https://pith.science/api/pith-number/ODAWM5ZWDBK3GXE7MDHKUQZXOK/graph.json","fetch_events":"https://pith.science/api/pith-number/ODAWM5ZWDBK3GXE7MDHKUQZXOK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ODAWM5ZWDBK3GXE7MDHKUQZXOK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ODAWM5ZWDBK3GXE7MDHKUQZXOK/action/storage_attestation","attest_author":"https://pith.science/pith/ODAWM5ZWDBK3GXE7MDHKUQZXOK/action/author_attestation","sign_citation":"https://pith.science/pith/ODAWM5ZWDBK3GXE7MDHKUQZXOK/action/citation_signature","submit_replication":"https://pith.science/pith/ODAWM5ZWDBK3GXE7MDHKUQZXOK/action/replication_record"}},"created_at":"2026-07-05T07:16:50.673682+00:00","updated_at":"2026-07-05T07:16:50.673682+00:00"}