{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:H7HJKSPMXIO7NEVCFACBCXK7PV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"14afe05b97d0a69623d7484666bcc991df9446948103554b3d7c2429a69dba7e","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-06-06T11:51:22Z","title_canon_sha256":"0507e7484c1986723fc0687f3a7d08e13a351445d3977bc643354f245bf4920a"},"schema_version":"1.0","source":{"id":"2206.02512","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.02512","created_at":"2026-07-05T09:16:05Z"},{"alias_kind":"arxiv_version","alias_value":"2206.02512v4","created_at":"2026-07-05T09:16:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02512","created_at":"2026-07-05T09:16:05Z"},{"alias_kind":"pith_short_12","alias_value":"H7HJKSPMXIO7","created_at":"2026-07-05T09:16:05Z"},{"alias_kind":"pith_short_16","alias_value":"H7HJKSPMXIO7NEVC","created_at":"2026-07-05T09:16:05Z"},{"alias_kind":"pith_short_8","alias_value":"H7HJKSPM","created_at":"2026-07-05T09:16:05Z"}],"graph_snapshots":[{"event_id":"sha256:6f6b82b2dab6ef7fc5b23b0be3644cded75363437fa6d3877654d15b9dc81d29","target":"graph","created_at":"2026-07-05T09:16:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2206.02512/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chunlei Zhang, Dong Yu, Gopala Krishna Anumanchipalli, Jiachen Lian","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-06-06T11:51:22Z","title":"Unsupervised TTS Acoustic Modeling for TTS with Conditional Disentangled Sequential VAE"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02512","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:db083abe52351e8d51a36c025fa887521f6d974ebf85e8be4b138ba8a52782cc","target":"record","created_at":"2026-07-05T09:16:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"14afe05b97d0a69623d7484666bcc991df9446948103554b3d7c2429a69dba7e","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-06-06T11:51:22Z","title_canon_sha256":"0507e7484c1986723fc0687f3a7d08e13a351445d3977bc643354f245bf4920a"},"schema_version":"1.0","source":{"id":"2206.02512","kind":"arxiv","version":4}},"canonical_sha256":"3fce9549ecba1df692a22804115d5f7d7efd1b085dcca3693522b6ab6f79405c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3fce9549ecba1df692a22804115d5f7d7efd1b085dcca3693522b6ab6f79405c","first_computed_at":"2026-07-05T09:16:05.601292Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:05.601292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"diZvqihFohRg1x1I9nfpfIHFh+pwmLw6KCzAT4YK70D3XusaZzysfihEu+yUNzc3zff8YCtP8tvbIMHALNGRBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:05.601855Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.02512","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db083abe52351e8d51a36c025fa887521f6d974ebf85e8be4b138ba8a52782cc","sha256:6f6b82b2dab6ef7fc5b23b0be3644cded75363437fa6d3877654d15b9dc81d29"],"state_sha256":"035d6128a98a916cde91817cdba6c5892624484518b617323774d6b4b94b073a"}