{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:P2SF5A73DFQSWORG4DMUPF6YO6","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":"875613fe4d0a9fab5b149e510bb3ab33357a98302cab5a71d5fe6d19f97c7675","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-08-14T01:01:19Z","title_canon_sha256":"ce979c30ef50c478e1599da61f4251eb102e036038006cda1f9287805ae64e2b"},"schema_version":"1.0","source":{"id":"2308.06873","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.06873","created_at":"2026-07-05T08:36:43Z"},{"alias_kind":"arxiv_version","alias_value":"2308.06873v2","created_at":"2026-07-05T08:36:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.06873","created_at":"2026-07-05T08:36:43Z"},{"alias_kind":"pith_short_12","alias_value":"P2SF5A73DFQS","created_at":"2026-07-05T08:36:43Z"},{"alias_kind":"pith_short_16","alias_value":"P2SF5A73DFQSWORG","created_at":"2026-07-05T08:36:43Z"},{"alias_kind":"pith_short_8","alias_value":"P2SF5A73","created_at":"2026-07-05T08:36:43Z"}],"graph_snapshots":[{"event_id":"sha256:ba0fc68297f2aa2d2ca02324761061067b77892f0d3289bce81bdaa860b1e70a","target":"graph","created_at":"2026-07-05T08:36:43Z","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/2308.06873/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in generative speech models based on audio-text prompts have enabled remarkable innovations like high-quality zero-shot text-to-speech. However, existing models still face limitations in handling diverse audio-text speech generation tasks involving transforming input speech and processing audio captured in adverse acoustic conditions. This paper introduces SpeechX, a versatile speech generation model capable of zero-shot TTS and various speech transformation tasks, dealing with both clean and noisy signals. SpeechX combines neural codec language modeling with multi-task lea","authors_text":"Jinyu Li, Manthan Thakker, Min Tang, Naoyuki Kanda, Sanyuan Chen, Sefik Emre Eskimez, Shujie Liu, Takuya Yoshioka, Xiaofei Wang, Zhuo Chen","cross_cats":["cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-08-14T01:01:19Z","title":"SpeechX: Neural Codec Language Model as a Versatile Speech Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.06873","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":"sha256:89fdada8414df6467c1b3d0a54e7bc9a5a64d6a0fd32c8c96a4f1e81ee0c612e","target":"record","created_at":"2026-07-05T08:36:43Z","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":"875613fe4d0a9fab5b149e510bb3ab33357a98302cab5a71d5fe6d19f97c7675","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-08-14T01:01:19Z","title_canon_sha256":"ce979c30ef50c478e1599da61f4251eb102e036038006cda1f9287805ae64e2b"},"schema_version":"1.0","source":{"id":"2308.06873","kind":"arxiv","version":2}},"canonical_sha256":"7ea45e83fb19612b3a26e0d94797d8778e6db3154cf14d465d4544c4711a2f98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ea45e83fb19612b3a26e0d94797d8778e6db3154cf14d465d4544c4711a2f98","first_computed_at":"2026-07-05T08:36:43.002698Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:43.002698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IKyN5ev5WiIv6iYqc1WOqzaBgczSj+TRmNmMHhlkEWhtbQOhmweikb7OjBX075PKOhtVUOjYRCDOy39FE3ngCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:43.003179Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.06873","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89fdada8414df6467c1b3d0a54e7bc9a5a64d6a0fd32c8c96a4f1e81ee0c612e","sha256:ba0fc68297f2aa2d2ca02324761061067b77892f0d3289bce81bdaa860b1e70a"],"state_sha256":"b7366f119de37dea57aa091bc310383e17fb7317a6c4ff5cb3d23cb1b9a66d66"}