{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VY3JI52ER2JEQMKY6ZELX7GZXJ","short_pith_number":"pith:VY3JI52E","canonical_record":{"source":{"id":"2306.07691","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-06-13T11:04:43Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"59ab1a5620cc5c81508c32ebe199366ccaf95c331d76287e83130f781f57ae91","abstract_canon_sha256":"8b446e6078a860e9c546dc21a9ef5d7e833968081f7c0dccb9a255b8efb55dae"},"schema_version":"1.0"},"canonical_sha256":"ae369477448e92483158f648bbfcd9ba5163f3c704875eae4c2334f378fe090a","source":{"kind":"arxiv","id":"2306.07691","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07691","created_at":"2026-07-05T07:14:13Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07691v2","created_at":"2026-07-05T07:14:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07691","created_at":"2026-07-05T07:14:13Z"},{"alias_kind":"pith_short_12","alias_value":"VY3JI52ER2JE","created_at":"2026-07-05T07:14:13Z"},{"alias_kind":"pith_short_16","alias_value":"VY3JI52ER2JEQMKY","created_at":"2026-07-05T07:14:13Z"},{"alias_kind":"pith_short_8","alias_value":"VY3JI52E","created_at":"2026-07-05T07:14:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VY3JI52ER2JEQMKY6ZELX7GZXJ","target":"record","payload":{"canonical_record":{"source":{"id":"2306.07691","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-06-13T11:04:43Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"59ab1a5620cc5c81508c32ebe199366ccaf95c331d76287e83130f781f57ae91","abstract_canon_sha256":"8b446e6078a860e9c546dc21a9ef5d7e833968081f7c0dccb9a255b8efb55dae"},"schema_version":"1.0"},"canonical_sha256":"ae369477448e92483158f648bbfcd9ba5163f3c704875eae4c2334f378fe090a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:13.826979Z","signature_b64":"Zdh3g3LW37/s6112bQjAlx+rRENPxMHayUm8hZfPX57+DIxW6cC3RLAAuAXcnT2vMWTw2ENroZM8W6Bh2diNCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae369477448e92483158f648bbfcd9ba5163f3c704875eae4c2334f378fe090a","last_reissued_at":"2026-07-05T07:14:13.826509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:13.826509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.07691","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:14:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PtpgGGOSUYTtMBMV6edLIzIVqyxcrZt26ZP2J9duJUk0j1oJkmicHgV2Zlums7AdCUn/V1LJKne5USaUwSrOAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:35:07.607096Z"},"content_sha256":"39257a9deb399bf4622c86674bdd9527925d68b291909b7b9c34755fe016eda8","schema_version":"1.0","event_id":"sha256:39257a9deb399bf4622c86674bdd9527925d68b291909b7b9c34755fe016eda8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VY3JI52ER2JEQMKY6ZELX7GZXJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Cong Han, Gavin Mischler, Nima Mesgarani, Vinay S. Raghavan, Yinghao Aaron Li","submitted_at":"2023-06-13T11:04:43Z","abstract_excerpt":"In this paper, we present StyleTTS 2, a text-to-speech (TTS) model that leverages style diffusion and adversarial training with large speech language models (SLMs) to achieve human-level TTS synthesis. StyleTTS 2 differs from its predecessor by modeling styles as a latent random variable through diffusion models to generate the most suitable style for the text without requiring reference speech, achieving efficient latent diffusion while benefiting from the diverse speech synthesis offered by diffusion models. Furthermore, we employ large pre-trained SLMs, such as WavLM, as discriminators with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07691","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/2306.07691/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:14:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gh+/722grtTIOujEZnuWW9vv4xFXK2lgxQo0lf5t8ET399Mxsk8TTO9Df6vnB6BN4Nbq6JO7lWYVVlCohSW3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:35:07.608140Z"},"content_sha256":"e450f4122d77610136eadbcf24e5fc49069320c5b80d3b966100704b47fcdfdb","schema_version":"1.0","event_id":"sha256:e450f4122d77610136eadbcf24e5fc49069320c5b80d3b966100704b47fcdfdb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VY3JI52ER2JEQMKY6ZELX7GZXJ/bundle.json","state_url":"https://pith.science/pith/VY3JI52ER2JEQMKY6ZELX7GZXJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VY3JI52ER2JEQMKY6ZELX7GZXJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T20:35:07Z","links":{"resolver":"https://pith.science/pith/VY3JI52ER2JEQMKY6ZELX7GZXJ","bundle":"https://pith.science/pith/VY3JI52ER2JEQMKY6ZELX7GZXJ/bundle.json","state":"https://pith.science/pith/VY3JI52ER2JEQMKY6ZELX7GZXJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VY3JI52ER2JEQMKY6ZELX7GZXJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VY3JI52ER2JEQMKY6ZELX7GZXJ","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":"8b446e6078a860e9c546dc21a9ef5d7e833968081f7c0dccb9a255b8efb55dae","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-06-13T11:04:43Z","title_canon_sha256":"59ab1a5620cc5c81508c32ebe199366ccaf95c331d76287e83130f781f57ae91"},"schema_version":"1.0","source":{"id":"2306.07691","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07691","created_at":"2026-07-05T07:14:13Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07691v2","created_at":"2026-07-05T07:14:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07691","created_at":"2026-07-05T07:14:13Z"},{"alias_kind":"pith_short_12","alias_value":"VY3JI52ER2JE","created_at":"2026-07-05T07:14:13Z"},{"alias_kind":"pith_short_16","alias_value":"VY3JI52ER2JEQMKY","created_at":"2026-07-05T07:14:13Z"},{"alias_kind":"pith_short_8","alias_value":"VY3JI52E","created_at":"2026-07-05T07:14:13Z"}],"graph_snapshots":[{"event_id":"sha256:e450f4122d77610136eadbcf24e5fc49069320c5b80d3b966100704b47fcdfdb","target":"graph","created_at":"2026-07-05T07:14:13Z","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/2306.07691/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present StyleTTS 2, a text-to-speech (TTS) model that leverages style diffusion and adversarial training with large speech language models (SLMs) to achieve human-level TTS synthesis. StyleTTS 2 differs from its predecessor by modeling styles as a latent random variable through diffusion models to generate the most suitable style for the text without requiring reference speech, achieving efficient latent diffusion while benefiting from the diverse speech synthesis offered by diffusion models. Furthermore, we employ large pre-trained SLMs, such as WavLM, as discriminators with","authors_text":"Cong Han, Gavin Mischler, Nima Mesgarani, Vinay S. Raghavan, Yinghao Aaron Li","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-06-13T11:04:43Z","title":"StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07691","kind":"arxiv","version":2},"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":"sha256:39257a9deb399bf4622c86674bdd9527925d68b291909b7b9c34755fe016eda8","target":"record","created_at":"2026-07-05T07:14:13Z","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":"8b446e6078a860e9c546dc21a9ef5d7e833968081f7c0dccb9a255b8efb55dae","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-06-13T11:04:43Z","title_canon_sha256":"59ab1a5620cc5c81508c32ebe199366ccaf95c331d76287e83130f781f57ae91"},"schema_version":"1.0","source":{"id":"2306.07691","kind":"arxiv","version":2}},"canonical_sha256":"ae369477448e92483158f648bbfcd9ba5163f3c704875eae4c2334f378fe090a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae369477448e92483158f648bbfcd9ba5163f3c704875eae4c2334f378fe090a","first_computed_at":"2026-07-05T07:14:13.826509Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:14:13.826509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zdh3g3LW37/s6112bQjAlx+rRENPxMHayUm8hZfPX57+DIxW6cC3RLAAuAXcnT2vMWTw2ENroZM8W6Bh2diNCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:14:13.826979Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.07691","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39257a9deb399bf4622c86674bdd9527925d68b291909b7b9c34755fe016eda8","sha256:e450f4122d77610136eadbcf24e5fc49069320c5b80d3b966100704b47fcdfdb"],"state_sha256":"06bf9370dd86cebde88ce5fad0c078f2aaceb49d4baed53d2dcadb57b5e10020"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6+6satr0ZajdV01Ia8C0MzFN/v/slBpoAsvI0O6N1FHFt/jjrCjN+IYlI1myL1P6XNlbWMUVW7LbnrGkYTZUCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T20:35:07.635237Z","bundle_sha256":"73711571019e6856d54044689a90182d51faf75196a642f3ab07736350996c64"}}