{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QXPFTMQ7B4XPMYWXOFSRK66AS4","short_pith_number":"pith:QXPFTMQ7","schema_version":"1.0","canonical_sha256":"85de59b21f0f2ef662d77165157bc097344d2a72cc449030cf01125d23bec698","source":{"kind":"arxiv","id":"2607.23027","version":1},"attestation_state":"computed","paper":{"title":"Singlish, Can or Not? Fine-Tuning and Evaluating Zero-Shot TTS for Singapore English","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Ivan Kukanov, Zheng Xin Chai","submitted_at":"2026-07-25T03:59:26Z","abstract_excerpt":"Zero-shot text-to-speech (ZS-TTS) achieves near-human quality for standard English, but it copies regional accents poorly. Prompted with a short Singlish utterance, state-of-the-art systems reproduce a speaker's timbre while flattening the accent toward generic English. We investigate whether targeted fine-tuning off-the-shelf ZS-TTS can close the gap for Singapore English (Singlish). We fine-tune two cutting-edge ZS-TTS models, Chatterbox and CosyVoice 3, on 50 Singlish speakers from the IMDA National Speech Corpus. Three speech distributions are evaluated: real recordings against off-the-she"},"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":"2607.23027","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-25T03:59:26Z","cross_cats_sorted":[],"title_canon_sha256":"422d14ef2c9ae62eca5a37e74cd8984147e37ee3ea6bb483f368a44a7f320fd4","abstract_canon_sha256":"037993caac172f93c84e92f6196fc12a270789ed3f3b6c505fc394d813ba0d70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T00:22:08.360256Z","signature_b64":"gDBhV9wU+CqTYSSQ3b4AxdpT89kP5j+P2LJIKIGGLUjM/hrUafwt3BlZBcUyuMHzLajjbMhXGyaz7+z3I0hcCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85de59b21f0f2ef662d77165157bc097344d2a72cc449030cf01125d23bec698","last_reissued_at":"2026-07-28T00:22:08.359450Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T00:22:08.359450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Singlish, Can or Not? Fine-Tuning and Evaluating Zero-Shot TTS for Singapore English","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Ivan Kukanov, Zheng Xin Chai","submitted_at":"2026-07-25T03:59:26Z","abstract_excerpt":"Zero-shot text-to-speech (ZS-TTS) achieves near-human quality for standard English, but it copies regional accents poorly. Prompted with a short Singlish utterance, state-of-the-art systems reproduce a speaker's timbre while flattening the accent toward generic English. We investigate whether targeted fine-tuning off-the-shelf ZS-TTS can close the gap for Singapore English (Singlish). We fine-tune two cutting-edge ZS-TTS models, Chatterbox and CosyVoice 3, on 50 Singlish speakers from the IMDA National Speech Corpus. Three speech distributions are evaluated: real recordings against off-the-she"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23027","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/2607.23027/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":"2607.23027","created_at":"2026-07-28T00:22:08.359868+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.23027v1","created_at":"2026-07-28T00:22:08.359868+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23027","created_at":"2026-07-28T00:22:08.359868+00:00"},{"alias_kind":"pith_short_12","alias_value":"QXPFTMQ7B4XP","created_at":"2026-07-28T00:22:08.359868+00:00"},{"alias_kind":"pith_short_16","alias_value":"QXPFTMQ7B4XPMYWX","created_at":"2026-07-28T00:22:08.359868+00:00"},{"alias_kind":"pith_short_8","alias_value":"QXPFTMQ7","created_at":"2026-07-28T00:22:08.359868+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/QXPFTMQ7B4XPMYWXOFSRK66AS4","json":"https://pith.science/pith/QXPFTMQ7B4XPMYWXOFSRK66AS4.json","graph_json":"https://pith.science/api/pith-number/QXPFTMQ7B4XPMYWXOFSRK66AS4/graph.json","events_json":"https://pith.science/api/pith-number/QXPFTMQ7B4XPMYWXOFSRK66AS4/events.json","paper":"https://pith.science/paper/QXPFTMQ7"},"agent_actions":{"view_html":"https://pith.science/pith/QXPFTMQ7B4XPMYWXOFSRK66AS4","download_json":"https://pith.science/pith/QXPFTMQ7B4XPMYWXOFSRK66AS4.json","view_paper":"https://pith.science/paper/QXPFTMQ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.23027&json=true","fetch_graph":"https://pith.science/api/pith-number/QXPFTMQ7B4XPMYWXOFSRK66AS4/graph.json","fetch_events":"https://pith.science/api/pith-number/QXPFTMQ7B4XPMYWXOFSRK66AS4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QXPFTMQ7B4XPMYWXOFSRK66AS4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QXPFTMQ7B4XPMYWXOFSRK66AS4/action/storage_attestation","attest_author":"https://pith.science/pith/QXPFTMQ7B4XPMYWXOFSRK66AS4/action/author_attestation","sign_citation":"https://pith.science/pith/QXPFTMQ7B4XPMYWXOFSRK66AS4/action/citation_signature","submit_replication":"https://pith.science/pith/QXPFTMQ7B4XPMYWXOFSRK66AS4/action/replication_record"}},"created_at":"2026-07-28T00:22:08.359868+00:00","updated_at":"2026-07-28T00:22:08.359868+00:00"}