{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:P2SF5A73DFQSWORG4DMUPF6YO6","short_pith_number":"pith:P2SF5A73","schema_version":"1.0","canonical_sha256":"7ea45e83fb19612b3a26e0d94797d8778e6db3154cf14d465d4544c4711a2f98","source":{"kind":"arxiv","id":"2308.06873","version":2},"attestation_state":"computed","paper":{"title":"SpeechX: Neural Codec Language Model as a Versatile Speech Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jinyu Li, Manthan Thakker, Min Tang, Naoyuki Kanda, Sanyuan Chen, Sefik Emre Eskimez, Shujie Liu, Takuya Yoshioka, Xiaofei Wang, Zhuo Chen","submitted_at":"2023-08-14T01:01:19Z","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"},"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":"2308.06873","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-08-14T01:01:19Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"ce979c30ef50c478e1599da61f4251eb102e036038006cda1f9287805ae64e2b","abstract_canon_sha256":"875613fe4d0a9fab5b149e510bb3ab33357a98302cab5a71d5fe6d19f97c7675"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:43.003179Z","signature_b64":"IKyN5ev5WiIv6iYqc1WOqzaBgczSj+TRmNmMHhlkEWhtbQOhmweikb7OjBX075PKOhtVUOjYRCDOy39FE3ngCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ea45e83fb19612b3a26e0d94797d8778e6db3154cf14d465d4544c4711a2f98","last_reissued_at":"2026-07-05T08:36:43.002698Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:43.002698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpeechX: Neural Codec Language Model as a Versatile Speech Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jinyu Li, Manthan Thakker, Min Tang, Naoyuki Kanda, Sanyuan Chen, Sefik Emre Eskimez, Shujie Liu, Takuya Yoshioka, Xiaofei Wang, Zhuo Chen","submitted_at":"2023-08-14T01:01:19Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.06873","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/2308.06873/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":"2308.06873","created_at":"2026-07-05T08:36:43.002755+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.06873v2","created_at":"2026-07-05T08:36:43.002755+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.06873","created_at":"2026-07-05T08:36:43.002755+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2SF5A73DFQS","created_at":"2026-07-05T08:36:43.002755+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2SF5A73DFQSWORG","created_at":"2026-07-05T08:36:43.002755+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2SF5A73","created_at":"2026-07-05T08:36:43.002755+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.14294","citing_title":"DASB - Discrete Audio and Speech Benchmark","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2509.11717","citing_title":"CodecSep: Prompt-Driven Universal Sound Separation on Neural Audio Codec Latents","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2406.02430","citing_title":"Seed-TTS: A Family of High-Quality Versatile Speech Generation Models","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P2SF5A73DFQSWORG4DMUPF6YO6","json":"https://pith.science/pith/P2SF5A73DFQSWORG4DMUPF6YO6.json","graph_json":"https://pith.science/api/pith-number/P2SF5A73DFQSWORG4DMUPF6YO6/graph.json","events_json":"https://pith.science/api/pith-number/P2SF5A73DFQSWORG4DMUPF6YO6/events.json","paper":"https://pith.science/paper/P2SF5A73"},"agent_actions":{"view_html":"https://pith.science/pith/P2SF5A73DFQSWORG4DMUPF6YO6","download_json":"https://pith.science/pith/P2SF5A73DFQSWORG4DMUPF6YO6.json","view_paper":"https://pith.science/paper/P2SF5A73","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.06873&json=true","fetch_graph":"https://pith.science/api/pith-number/P2SF5A73DFQSWORG4DMUPF6YO6/graph.json","fetch_events":"https://pith.science/api/pith-number/P2SF5A73DFQSWORG4DMUPF6YO6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2SF5A73DFQSWORG4DMUPF6YO6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2SF5A73DFQSWORG4DMUPF6YO6/action/storage_attestation","attest_author":"https://pith.science/pith/P2SF5A73DFQSWORG4DMUPF6YO6/action/author_attestation","sign_citation":"https://pith.science/pith/P2SF5A73DFQSWORG4DMUPF6YO6/action/citation_signature","submit_replication":"https://pith.science/pith/P2SF5A73DFQSWORG4DMUPF6YO6/action/replication_record"}},"created_at":"2026-07-05T08:36:43.002755+00:00","updated_at":"2026-07-05T08:36:43.002755+00:00"}