{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IZ345MUDLVLOMEVXB7U4LLPD7B","short_pith_number":"pith:IZ345MUD","schema_version":"1.0","canonical_sha256":"4677ceb2835d56e612b70fe9c5ade3f8560e2d2787bcc6889a0383c9e9eb204e","source":{"kind":"arxiv","id":"2606.22811","version":1},"attestation_state":"computed","paper":{"title":"Bagpiper-TTS: Natural Language Guided Universal Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chao-Han Huck Yang, Haoran Wang, Jinchuan Tian, Jin Sakuma, Keita Goto, Shinji Watanabe, Siddhant Arora, Takashi Maekaku, Yusuke Shinohara","submitted_at":"2026-06-22T03:40:28Z","abstract_excerpt":"Classical TTS systems typically rely on rigid input formats and predefined metadata slots, limiting their ability to fulfill flexible user requirements. This paper introduces Bagpiper-TTS, a universal speech synthesis system that deals with diverse natural language user requests. Given a natural language prompt, Bagpiper-TTS first reasons over the users' intent to derive a rich caption, i.e., a comprehensive textual blueprint encompassing both transcription and nuanced metadata. Subsequently, this caption guides the synthesis of the target speech. Our model inherently supports a broad spectrum"},"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":"2606.22811","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-22T03:40:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f34e3045c015c66132e4fc6f607f7c39352a74063c942d155d94bbedac44e06e","abstract_canon_sha256":"8d6751cc187f6df31455ca27109ade6eab7631a25b405ada06ea80efa22332fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:14:00.041680Z","signature_b64":"zKloir13tfq4RjyAVrSZVk20tt9+3sqdKUVj4PAq44IhqRAdMBS0Lkn19DV0MNfzMWlHvnipSyTqJiSsQlMSCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4677ceb2835d56e612b70fe9c5ade3f8560e2d2787bcc6889a0383c9e9eb204e","last_reissued_at":"2026-06-23T02:14:00.041252Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:14:00.041252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bagpiper-TTS: Natural Language Guided Universal Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chao-Han Huck Yang, Haoran Wang, Jinchuan Tian, Jin Sakuma, Keita Goto, Shinji Watanabe, Siddhant Arora, Takashi Maekaku, Yusuke Shinohara","submitted_at":"2026-06-22T03:40:28Z","abstract_excerpt":"Classical TTS systems typically rely on rigid input formats and predefined metadata slots, limiting their ability to fulfill flexible user requirements. This paper introduces Bagpiper-TTS, a universal speech synthesis system that deals with diverse natural language user requests. Given a natural language prompt, Bagpiper-TTS first reasons over the users' intent to derive a rich caption, i.e., a comprehensive textual blueprint encompassing both transcription and nuanced metadata. Subsequently, this caption guides the synthesis of the target speech. Our model inherently supports a broad spectrum"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22811","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/2606.22811/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":"2606.22811","created_at":"2026-06-23T02:14:00.041328+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22811v1","created_at":"2026-06-23T02:14:00.041328+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22811","created_at":"2026-06-23T02:14:00.041328+00:00"},{"alias_kind":"pith_short_12","alias_value":"IZ345MUDLVLO","created_at":"2026-06-23T02:14:00.041328+00:00"},{"alias_kind":"pith_short_16","alias_value":"IZ345MUDLVLOMEVX","created_at":"2026-06-23T02:14:00.041328+00:00"},{"alias_kind":"pith_short_8","alias_value":"IZ345MUD","created_at":"2026-06-23T02:14:00.041328+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/IZ345MUDLVLOMEVXB7U4LLPD7B","json":"https://pith.science/pith/IZ345MUDLVLOMEVXB7U4LLPD7B.json","graph_json":"https://pith.science/api/pith-number/IZ345MUDLVLOMEVXB7U4LLPD7B/graph.json","events_json":"https://pith.science/api/pith-number/IZ345MUDLVLOMEVXB7U4LLPD7B/events.json","paper":"https://pith.science/paper/IZ345MUD"},"agent_actions":{"view_html":"https://pith.science/pith/IZ345MUDLVLOMEVXB7U4LLPD7B","download_json":"https://pith.science/pith/IZ345MUDLVLOMEVXB7U4LLPD7B.json","view_paper":"https://pith.science/paper/IZ345MUD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22811&json=true","fetch_graph":"https://pith.science/api/pith-number/IZ345MUDLVLOMEVXB7U4LLPD7B/graph.json","fetch_events":"https://pith.science/api/pith-number/IZ345MUDLVLOMEVXB7U4LLPD7B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IZ345MUDLVLOMEVXB7U4LLPD7B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IZ345MUDLVLOMEVXB7U4LLPD7B/action/storage_attestation","attest_author":"https://pith.science/pith/IZ345MUDLVLOMEVXB7U4LLPD7B/action/author_attestation","sign_citation":"https://pith.science/pith/IZ345MUDLVLOMEVXB7U4LLPD7B/action/citation_signature","submit_replication":"https://pith.science/pith/IZ345MUDLVLOMEVXB7U4LLPD7B/action/replication_record"}},"created_at":"2026-06-23T02:14:00.041328+00:00","updated_at":"2026-06-23T02:14:00.041328+00:00"}