{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AU7NTGP5MYNTTVHGBIYKFN54L2","short_pith_number":"pith:AU7NTGP5","schema_version":"1.0","canonical_sha256":"053ed999fd661b39d4e60a30a2b7bc5e86ffc4144fa4b79d68e995a70c46a7e8","source":{"kind":"arxiv","id":"2505.04113","version":2},"attestation_state":"computed","paper":{"title":"Advancing Zero-shot Text-to-Speech Intelligibility across Diverse Domains via Preference Alignment","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chaoren Wang, Xueyao Zhang, Yuancheng Wang, Zhizheng Wu, Zhuo Chen, Ziniu Li","submitted_at":"2025-05-07T04:04:31Z","abstract_excerpt":"Modern zero-shot text-to-speech (TTS) systems, despite using extensive pre-training, often struggle in challenging scenarios such as tongue twisters, repeated words, code-switching, and cross-lingual synthesis, leading to intelligibility issues. To address these limitations, this paper leverages preference alignment techniques, which enable targeted construction of out-of-pretraining-distribution data to enhance performance. We introduce a new dataset, named the Intelligibility Preference Speech Dataset (INTP), and extend the Direct Preference Optimization (DPO) framework to accommodate divers"},"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":"2505.04113","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-07T04:04:31Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"5d72dbe87bffa6e3307a6c490988a1d9c1ba403254ceaac3db1b2103f6fd1186","abstract_canon_sha256":"65ee6d3a4159cc270ae5dff1bf62c2d74b883dd47fdecf8e4f31828cc2f269d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:58.063556Z","signature_b64":"oYZ+gcNmA1bEQiBdaiEIl8nGyXzIYWMeCYV5VMfgpxbm3aUmwNNj2f3vflEy8XvaZXLbTUmrzSA7YOd1XjtXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"053ed999fd661b39d4e60a30a2b7bc5e86ffc4144fa4b79d68e995a70c46a7e8","last_reissued_at":"2026-07-05T11:16:58.063023Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:58.063023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advancing Zero-shot Text-to-Speech Intelligibility across Diverse Domains via Preference Alignment","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chaoren Wang, Xueyao Zhang, Yuancheng Wang, Zhizheng Wu, Zhuo Chen, Ziniu Li","submitted_at":"2025-05-07T04:04:31Z","abstract_excerpt":"Modern zero-shot text-to-speech (TTS) systems, despite using extensive pre-training, often struggle in challenging scenarios such as tongue twisters, repeated words, code-switching, and cross-lingual synthesis, leading to intelligibility issues. To address these limitations, this paper leverages preference alignment techniques, which enable targeted construction of out-of-pretraining-distribution data to enhance performance. We introduce a new dataset, named the Intelligibility Preference Speech Dataset (INTP), and extend the Direct Preference Optimization (DPO) framework to accommodate divers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04113","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/2505.04113/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":"2505.04113","created_at":"2026-07-05T11:16:58.063085+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.04113v2","created_at":"2026-07-05T11:16:58.063085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04113","created_at":"2026-07-05T11:16:58.063085+00:00"},{"alias_kind":"pith_short_12","alias_value":"AU7NTGP5MYNT","created_at":"2026-07-05T11:16:58.063085+00:00"},{"alias_kind":"pith_short_16","alias_value":"AU7NTGP5MYNTTVHG","created_at":"2026-07-05T11:16:58.063085+00:00"},{"alias_kind":"pith_short_8","alias_value":"AU7NTGP5","created_at":"2026-07-05T11:16:58.063085+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31247","citing_title":"FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model","ref_index":237,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11219","citing_title":"Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents","ref_index":160,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AU7NTGP5MYNTTVHGBIYKFN54L2","json":"https://pith.science/pith/AU7NTGP5MYNTTVHGBIYKFN54L2.json","graph_json":"https://pith.science/api/pith-number/AU7NTGP5MYNTTVHGBIYKFN54L2/graph.json","events_json":"https://pith.science/api/pith-number/AU7NTGP5MYNTTVHGBIYKFN54L2/events.json","paper":"https://pith.science/paper/AU7NTGP5"},"agent_actions":{"view_html":"https://pith.science/pith/AU7NTGP5MYNTTVHGBIYKFN54L2","download_json":"https://pith.science/pith/AU7NTGP5MYNTTVHGBIYKFN54L2.json","view_paper":"https://pith.science/paper/AU7NTGP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.04113&json=true","fetch_graph":"https://pith.science/api/pith-number/AU7NTGP5MYNTTVHGBIYKFN54L2/graph.json","fetch_events":"https://pith.science/api/pith-number/AU7NTGP5MYNTTVHGBIYKFN54L2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AU7NTGP5MYNTTVHGBIYKFN54L2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AU7NTGP5MYNTTVHGBIYKFN54L2/action/storage_attestation","attest_author":"https://pith.science/pith/AU7NTGP5MYNTTVHGBIYKFN54L2/action/author_attestation","sign_citation":"https://pith.science/pith/AU7NTGP5MYNTTVHGBIYKFN54L2/action/citation_signature","submit_replication":"https://pith.science/pith/AU7NTGP5MYNTTVHGBIYKFN54L2/action/replication_record"}},"created_at":"2026-07-05T11:16:58.063085+00:00","updated_at":"2026-07-05T11:16:58.063085+00:00"}