{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HJXMJNLLGMZKDHCS6P2PMIYNDO","short_pith_number":"pith:HJXMJNLL","schema_version":"1.0","canonical_sha256":"3a6ec4b56b3332a19c52f3f4f6230d1bbdedc8c50a45ed506c09bdbb21f52575","source":{"kind":"arxiv","id":"2305.13612","version":1},"attestation_state":"computed","paper":{"title":"FluentSpeech: Stutter-Oriented Automatic Speech Editing with Context-Aware Diffusion Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jialong Zuo, Qian Yang, Rongjie Huang, Yi Ren, Zhenhui Ye, Zhou Zhao, Ziyue Jiang","submitted_at":"2023-05-23T02:20:47Z","abstract_excerpt":"Stutter removal is an essential scenario in the field of speech editing. However, when the speech recording contains stutters, the existing text-based speech editing approaches still suffer from: 1) the over-smoothing problem in the edited speech; 2) lack of robustness due to the noise introduced by stutter; 3) to remove the stutters, users are required to determine the edited region manually. To tackle the challenges in stutter removal, we propose FluentSpeech, a stutter-oriented automatic speech editing model. Specifically, 1) we propose a context-aware diffusion model that iteratively refin"},"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":"2305.13612","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-23T02:20:47Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"4750ecf523d5a466aaedce349e8a01ee1a2df15f6f6bb31b329d7b98e3eee0c3","abstract_canon_sha256":"b7283f3b02dbe06b9f1641584d65c03cea2af6950cb77d8e6c190c5d9fdaff9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:54.940490Z","signature_b64":"oztWw7OhREUZxwvHD6pa8/hrObYemwul+QwJzuPEA2kOKCnmsTrLbhapX0l9YXNt8+KOBUu1857JK+0scPUCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a6ec4b56b3332a19c52f3f4f6230d1bbdedc8c50a45ed506c09bdbb21f52575","last_reissued_at":"2026-07-05T06:12:54.939993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:54.939993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FluentSpeech: Stutter-Oriented Automatic Speech Editing with Context-Aware Diffusion Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jialong Zuo, Qian Yang, Rongjie Huang, Yi Ren, Zhenhui Ye, Zhou Zhao, Ziyue Jiang","submitted_at":"2023-05-23T02:20:47Z","abstract_excerpt":"Stutter removal is an essential scenario in the field of speech editing. However, when the speech recording contains stutters, the existing text-based speech editing approaches still suffer from: 1) the over-smoothing problem in the edited speech; 2) lack of robustness due to the noise introduced by stutter; 3) to remove the stutters, users are required to determine the edited region manually. To tackle the challenges in stutter removal, we propose FluentSpeech, a stutter-oriented automatic speech editing model. Specifically, 1) we propose a context-aware diffusion model that iteratively refin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13612","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/2305.13612/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":"2305.13612","created_at":"2026-07-05T06:12:54.940055+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13612v1","created_at":"2026-07-05T06:12:54.940055+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13612","created_at":"2026-07-05T06:12:54.940055+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJXMJNLLGMZK","created_at":"2026-07-05T06:12:54.940055+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJXMJNLLGMZKDHCS","created_at":"2026-07-05T06:12:54.940055+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJXMJNLL","created_at":"2026-07-05T06:12:54.940055+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09282","citing_title":"ClaritySpeech: Dementia Obfuscation in Speech","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HJXMJNLLGMZKDHCS6P2PMIYNDO","json":"https://pith.science/pith/HJXMJNLLGMZKDHCS6P2PMIYNDO.json","graph_json":"https://pith.science/api/pith-number/HJXMJNLLGMZKDHCS6P2PMIYNDO/graph.json","events_json":"https://pith.science/api/pith-number/HJXMJNLLGMZKDHCS6P2PMIYNDO/events.json","paper":"https://pith.science/paper/HJXMJNLL"},"agent_actions":{"view_html":"https://pith.science/pith/HJXMJNLLGMZKDHCS6P2PMIYNDO","download_json":"https://pith.science/pith/HJXMJNLLGMZKDHCS6P2PMIYNDO.json","view_paper":"https://pith.science/paper/HJXMJNLL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13612&json=true","fetch_graph":"https://pith.science/api/pith-number/HJXMJNLLGMZKDHCS6P2PMIYNDO/graph.json","fetch_events":"https://pith.science/api/pith-number/HJXMJNLLGMZKDHCS6P2PMIYNDO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJXMJNLLGMZKDHCS6P2PMIYNDO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJXMJNLLGMZKDHCS6P2PMIYNDO/action/storage_attestation","attest_author":"https://pith.science/pith/HJXMJNLLGMZKDHCS6P2PMIYNDO/action/author_attestation","sign_citation":"https://pith.science/pith/HJXMJNLLGMZKDHCS6P2PMIYNDO/action/citation_signature","submit_replication":"https://pith.science/pith/HJXMJNLLGMZKDHCS6P2PMIYNDO/action/replication_record"}},"created_at":"2026-07-05T06:12:54.940055+00:00","updated_at":"2026-07-05T06:12:54.940055+00:00"}