{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:H7HJKSPMXIO7NEVCFACBCXK7PV","short_pith_number":"pith:H7HJKSPM","schema_version":"1.0","canonical_sha256":"3fce9549ecba1df692a22804115d5f7d7efd1b085dcca3693522b6ab6f79405c","source":{"kind":"arxiv","id":"2206.02512","version":4},"attestation_state":"computed","paper":{"title":"Unsupervised TTS Acoustic Modeling for TTS with Conditional Disentangled Sequential VAE","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chunlei Zhang, Dong Yu, Gopala Krishna Anumanchipalli, Jiachen Lian","submitted_at":"2022-06-06T11:51:22Z","abstract_excerpt":"In this paper, we propose a novel unsupervised text-to-speech acoustic model training scheme, named UTTS, which does not require text-audio pairs. UTTS is a multi-speaker speech synthesizer that supports zero-shot voice cloning, it is developed from a perspective of disentangled speech representation learning. The framework offers a flexible choice of a speaker's duration model, timbre feature (identity) and content for TTS inference. We leverage recent advancements in self-supervised speech representation learning as well as speech synthesis front-end techniques for system development. Specif"},"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":"2206.02512","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-06-06T11:51:22Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"0507e7484c1986723fc0687f3a7d08e13a351445d3977bc643354f245bf4920a","abstract_canon_sha256":"14afe05b97d0a69623d7484666bcc991df9446948103554b3d7c2429a69dba7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:05.601855Z","signature_b64":"diZvqihFohRg1x1I9nfpfIHFh+pwmLw6KCzAT4YK70D3XusaZzysfihEu+yUNzc3zff8YCtP8tvbIMHALNGRBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fce9549ecba1df692a22804115d5f7d7efd1b085dcca3693522b6ab6f79405c","last_reissued_at":"2026-07-05T09:16:05.601292Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:05.601292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised TTS Acoustic Modeling for TTS with Conditional Disentangled Sequential VAE","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chunlei Zhang, Dong Yu, Gopala Krishna Anumanchipalli, Jiachen Lian","submitted_at":"2022-06-06T11:51:22Z","abstract_excerpt":"In this paper, we propose a novel unsupervised text-to-speech acoustic model training scheme, named UTTS, which does not require text-audio pairs. UTTS is a multi-speaker speech synthesizer that supports zero-shot voice cloning, it is developed from a perspective of disentangled speech representation learning. The framework offers a flexible choice of a speaker's duration model, timbre feature (identity) and content for TTS inference. We leverage recent advancements in self-supervised speech representation learning as well as speech synthesis front-end techniques for system development. Specif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02512","kind":"arxiv","version":4},"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/2206.02512/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":"2206.02512","created_at":"2026-07-05T09:16:05.601391+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.02512v4","created_at":"2026-07-05T09:16:05.601391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02512","created_at":"2026-07-05T09:16:05.601391+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7HJKSPMXIO7","created_at":"2026-07-05T09:16:05.601391+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7HJKSPMXIO7NEVC","created_at":"2026-07-05T09:16:05.601391+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7HJKSPM","created_at":"2026-07-05T09:16:05.601391+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00265","citing_title":"SSDM 2.0: Time-Accurate Speech Rich Transcription with Non-Fluencies","ref_index":2023,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H7HJKSPMXIO7NEVCFACBCXK7PV","json":"https://pith.science/pith/H7HJKSPMXIO7NEVCFACBCXK7PV.json","graph_json":"https://pith.science/api/pith-number/H7HJKSPMXIO7NEVCFACBCXK7PV/graph.json","events_json":"https://pith.science/api/pith-number/H7HJKSPMXIO7NEVCFACBCXK7PV/events.json","paper":"https://pith.science/paper/H7HJKSPM"},"agent_actions":{"view_html":"https://pith.science/pith/H7HJKSPMXIO7NEVCFACBCXK7PV","download_json":"https://pith.science/pith/H7HJKSPMXIO7NEVCFACBCXK7PV.json","view_paper":"https://pith.science/paper/H7HJKSPM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.02512&json=true","fetch_graph":"https://pith.science/api/pith-number/H7HJKSPMXIO7NEVCFACBCXK7PV/graph.json","fetch_events":"https://pith.science/api/pith-number/H7HJKSPMXIO7NEVCFACBCXK7PV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7HJKSPMXIO7NEVCFACBCXK7PV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7HJKSPMXIO7NEVCFACBCXK7PV/action/storage_attestation","attest_author":"https://pith.science/pith/H7HJKSPMXIO7NEVCFACBCXK7PV/action/author_attestation","sign_citation":"https://pith.science/pith/H7HJKSPMXIO7NEVCFACBCXK7PV/action/citation_signature","submit_replication":"https://pith.science/pith/H7HJKSPMXIO7NEVCFACBCXK7PV/action/replication_record"}},"created_at":"2026-07-05T09:16:05.601391+00:00","updated_at":"2026-07-05T09:16:05.601391+00:00"}