{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JFQZBFRJMFLIHQNWG42AHBO7SZ","short_pith_number":"pith:JFQZBFRJ","schema_version":"1.0","canonical_sha256":"4961909629615683c1b637340385df9664025d863ed8c2f660bbeb3ef4dbb9a8","source":{"kind":"arxiv","id":"2409.07151","version":2},"attestation_state":"computed","paper":{"title":"Zero-Shot Text-to-Speech as Golden Speech Generator: A Systematic Framework and its Applicability in Automatic Pronunciation Assessment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"eess.AS","authors_text":"Berlin Chen, Meng-Ting Tsai, Tien-Hong Lo, Yao-Ting Sung","submitted_at":"2024-09-11T09:55:57Z","abstract_excerpt":"Second language (L2) learners can improve their pronunciation by imitating golden speech, especially when the speech that aligns with their respective speech characteristics. This study explores the hypothesis that learner-specific golden speech generated with zero-shot text-to-speech (ZS-TTS) techniques can be harnessed as an effective metric for measuring the pronunciation proficiency of L2 learners. Building on this exploration, the contributions of this study are at least two-fold: 1) design and development of a systematic framework for assessing the ability of a synthesis model to generat"},"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":"2409.07151","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-11T09:55:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"876d8e7ed4ef386fffdb0d43797c3106bd35c520285d60a32c49bce11d4cef2c","abstract_canon_sha256":"e8040fc4e574ba0f4dc93aea22b89ead8d03855353827cf3a5d7c83b3c0bf2e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:29.302071Z","signature_b64":"Po8PGqfeb0zWFwxcX5xL+ehGi0fNNvxdUXj4kGxnGebmkAqIfdY6sfakRJDmKnAKfdvUEUDbulY8jX69YnDNBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4961909629615683c1b637340385df9664025d863ed8c2f660bbeb3ef4dbb9a8","last_reissued_at":"2026-07-05T11:43:29.301653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:29.301653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Text-to-Speech as Golden Speech Generator: A Systematic Framework and its Applicability in Automatic Pronunciation Assessment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"eess.AS","authors_text":"Berlin Chen, Meng-Ting Tsai, Tien-Hong Lo, Yao-Ting Sung","submitted_at":"2024-09-11T09:55:57Z","abstract_excerpt":"Second language (L2) learners can improve their pronunciation by imitating golden speech, especially when the speech that aligns with their respective speech characteristics. This study explores the hypothesis that learner-specific golden speech generated with zero-shot text-to-speech (ZS-TTS) techniques can be harnessed as an effective metric for measuring the pronunciation proficiency of L2 learners. Building on this exploration, the contributions of this study are at least two-fold: 1) design and development of a systematic framework for assessing the ability of a synthesis model to generat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07151","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/2409.07151/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":"2409.07151","created_at":"2026-07-05T11:43:29.301708+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.07151v2","created_at":"2026-07-05T11:43:29.301708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07151","created_at":"2026-07-05T11:43:29.301708+00:00"},{"alias_kind":"pith_short_12","alias_value":"JFQZBFRJMFLI","created_at":"2026-07-05T11:43:29.301708+00:00"},{"alias_kind":"pith_short_16","alias_value":"JFQZBFRJMFLIHQNW","created_at":"2026-07-05T11:43:29.301708+00:00"},{"alias_kind":"pith_short_8","alias_value":"JFQZBFRJ","created_at":"2026-07-05T11:43:29.301708+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19910","citing_title":"Light-weight Pronunciation Assessment via Discrete Speech Token Surprisal","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JFQZBFRJMFLIHQNWG42AHBO7SZ","json":"https://pith.science/pith/JFQZBFRJMFLIHQNWG42AHBO7SZ.json","graph_json":"https://pith.science/api/pith-number/JFQZBFRJMFLIHQNWG42AHBO7SZ/graph.json","events_json":"https://pith.science/api/pith-number/JFQZBFRJMFLIHQNWG42AHBO7SZ/events.json","paper":"https://pith.science/paper/JFQZBFRJ"},"agent_actions":{"view_html":"https://pith.science/pith/JFQZBFRJMFLIHQNWG42AHBO7SZ","download_json":"https://pith.science/pith/JFQZBFRJMFLIHQNWG42AHBO7SZ.json","view_paper":"https://pith.science/paper/JFQZBFRJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.07151&json=true","fetch_graph":"https://pith.science/api/pith-number/JFQZBFRJMFLIHQNWG42AHBO7SZ/graph.json","fetch_events":"https://pith.science/api/pith-number/JFQZBFRJMFLIHQNWG42AHBO7SZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JFQZBFRJMFLIHQNWG42AHBO7SZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JFQZBFRJMFLIHQNWG42AHBO7SZ/action/storage_attestation","attest_author":"https://pith.science/pith/JFQZBFRJMFLIHQNWG42AHBO7SZ/action/author_attestation","sign_citation":"https://pith.science/pith/JFQZBFRJMFLIHQNWG42AHBO7SZ/action/citation_signature","submit_replication":"https://pith.science/pith/JFQZBFRJMFLIHQNWG42AHBO7SZ/action/replication_record"}},"created_at":"2026-07-05T11:43:29.301708+00:00","updated_at":"2026-07-05T11:43:29.301708+00:00"}