{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4CWPP5BKE3ITMTYUR7EKZ2O3UF","short_pith_number":"pith:4CWPP5BK","schema_version":"1.0","canonical_sha256":"e0acf7f42a26d1364f148fc8ace9dba15892fc894572995117bc1ee3b5a2fdf6","source":{"kind":"arxiv","id":"2506.12570","version":1},"attestation_state":"computed","paper":{"title":"StreamMel: Real-Time Zero-shot Text-to-Speech via Interleaved Continuous Autoregressive Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Haoqin Sun, Hui Wang, Jiaming Zhou, Jinyu Li, Lingwei Meng, Shujie Liu, Yan Lu, Yanqing Liu, Yifan Yang, Yong Qin","submitted_at":"2025-06-14T16:53:39Z","abstract_excerpt":"Recent advances in zero-shot text-to-speech (TTS) synthesis have achieved high-quality speech generation for unseen speakers, but most systems remain unsuitable for real-time applications because of their offline design. Current streaming TTS paradigms often rely on multi-stage pipelines and discrete representations, leading to increased computational cost and suboptimal system performance. In this work, we propose StreamMel, a pioneering single-stage streaming TTS framework that models continuous mel-spectrograms. By interleaving text tokens with acoustic frames, StreamMel enables low-latency"},"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":"2506.12570","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-14T16:53:39Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"3754115b5cdebad4f10c82248e03397ffaf4cee00d01f63cdfa69c3cd317c818","abstract_canon_sha256":"f8e68871dceb02feba4c54c38a5a6e0c4c78240f25221a2cb34f7ece415c427d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:55.548817Z","signature_b64":"u78o6a/YMw+uiUA/fiOIPbrwtIsP4diHsHm4lNjgeEqNOFKbHXEP7InE5H7eDQYhU3DNDnT9WCLp0r9Py9pgAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0acf7f42a26d1364f148fc8ace9dba15892fc894572995117bc1ee3b5a2fdf6","last_reissued_at":"2026-07-05T11:21:55.548329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:55.548329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StreamMel: Real-Time Zero-shot Text-to-Speech via Interleaved Continuous Autoregressive Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Haoqin Sun, Hui Wang, Jiaming Zhou, Jinyu Li, Lingwei Meng, Shujie Liu, Yan Lu, Yanqing Liu, Yifan Yang, Yong Qin","submitted_at":"2025-06-14T16:53:39Z","abstract_excerpt":"Recent advances in zero-shot text-to-speech (TTS) synthesis have achieved high-quality speech generation for unseen speakers, but most systems remain unsuitable for real-time applications because of their offline design. Current streaming TTS paradigms often rely on multi-stage pipelines and discrete representations, leading to increased computational cost and suboptimal system performance. In this work, we propose StreamMel, a pioneering single-stage streaming TTS framework that models continuous mel-spectrograms. By interleaving text tokens with acoustic frames, StreamMel enables low-latency"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12570","kind":"arxiv","version":1},"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/2506.12570/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":"2506.12570","created_at":"2026-07-05T11:21:55.548388+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.12570v1","created_at":"2026-07-05T11:21:55.548388+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12570","created_at":"2026-07-05T11:21:55.548388+00:00"},{"alias_kind":"pith_short_12","alias_value":"4CWPP5BKE3IT","created_at":"2026-07-05T11:21:55.548388+00:00"},{"alias_kind":"pith_short_16","alias_value":"4CWPP5BKE3ITMTYU","created_at":"2026-07-05T11:21:55.548388+00:00"},{"alias_kind":"pith_short_8","alias_value":"4CWPP5BK","created_at":"2026-07-05T11:21:55.548388+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4CWPP5BKE3ITMTYUR7EKZ2O3UF","json":"https://pith.science/pith/4CWPP5BKE3ITMTYUR7EKZ2O3UF.json","graph_json":"https://pith.science/api/pith-number/4CWPP5BKE3ITMTYUR7EKZ2O3UF/graph.json","events_json":"https://pith.science/api/pith-number/4CWPP5BKE3ITMTYUR7EKZ2O3UF/events.json","paper":"https://pith.science/paper/4CWPP5BK"},"agent_actions":{"view_html":"https://pith.science/pith/4CWPP5BKE3ITMTYUR7EKZ2O3UF","download_json":"https://pith.science/pith/4CWPP5BKE3ITMTYUR7EKZ2O3UF.json","view_paper":"https://pith.science/paper/4CWPP5BK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.12570&json=true","fetch_graph":"https://pith.science/api/pith-number/4CWPP5BKE3ITMTYUR7EKZ2O3UF/graph.json","fetch_events":"https://pith.science/api/pith-number/4CWPP5BKE3ITMTYUR7EKZ2O3UF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4CWPP5BKE3ITMTYUR7EKZ2O3UF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4CWPP5BKE3ITMTYUR7EKZ2O3UF/action/storage_attestation","attest_author":"https://pith.science/pith/4CWPP5BKE3ITMTYUR7EKZ2O3UF/action/author_attestation","sign_citation":"https://pith.science/pith/4CWPP5BKE3ITMTYUR7EKZ2O3UF/action/citation_signature","submit_replication":"https://pith.science/pith/4CWPP5BKE3ITMTYUR7EKZ2O3UF/action/replication_record"}},"created_at":"2026-07-05T11:21:55.548388+00:00","updated_at":"2026-07-05T11:21:55.548388+00:00"}