{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2PVEW54KT63CS4XTVYQDQXJKA3","short_pith_number":"pith:2PVEW54K","schema_version":"1.0","canonical_sha256":"d3ea4b778a9fb62972f3ae20385d2a06ffb2457b0e7fa946865527daf22582ce","source":{"kind":"arxiv","id":"2102.08328","version":1},"attestation_state":"computed","paper":{"title":"Context-Aware Prosody Correction for Text-Based Speech Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Bryan Pardo, Juan-Pablo Caceres, Lucas Rencker, Max Morrison, Nicholas J. Bryan, Zeyu Jin","submitted_at":"2021-02-16T18:16:30Z","abstract_excerpt":"Text-based speech editors expedite the process of editing speech recordings by permitting editing via intuitive cut, copy, and paste operations on a speech transcript. A major drawback of current systems, however, is that edited recordings often sound unnatural because of prosody mismatches around edited regions. In our work, we propose a new context-aware method for more natural sounding text-based editing of speech. To do so, we 1) use a series of neural networks to generate salient prosody features that are dependent on the prosody of speech surrounding the edit and amenable to fine-grained"},"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":"2102.08328","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-02-16T18:16:30Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"60d0f9f9a17baa09b1c8b196ba27646c7804781e8c6719191fec5fff73dfa961","abstract_canon_sha256":"ad453c3162a9ac2878faaca65b35471fdd729361aa90a6c618de9176175a4058"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:15:48.510679Z","signature_b64":"krqtiZlpMDqyrYHKIBc2few1xWQBYSq+wMa6cNScQ3ug8FGDinOfxbeBfa8xJURucWUbe+HlYowVinhJYO1lDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3ea4b778a9fb62972f3ae20385d2a06ffb2457b0e7fa946865527daf22582ce","last_reissued_at":"2026-07-05T02:15:48.510027Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:15:48.510027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Context-Aware Prosody Correction for Text-Based Speech Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Bryan Pardo, Juan-Pablo Caceres, Lucas Rencker, Max Morrison, Nicholas J. Bryan, Zeyu Jin","submitted_at":"2021-02-16T18:16:30Z","abstract_excerpt":"Text-based speech editors expedite the process of editing speech recordings by permitting editing via intuitive cut, copy, and paste operations on a speech transcript. A major drawback of current systems, however, is that edited recordings often sound unnatural because of prosody mismatches around edited regions. In our work, we propose a new context-aware method for more natural sounding text-based editing of speech. To do so, we 1) use a series of neural networks to generate salient prosody features that are dependent on the prosody of speech surrounding the edit and amenable to fine-grained"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.08328","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/2102.08328/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":"2102.08328","created_at":"2026-07-05T02:15:48.510093+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.08328v1","created_at":"2026-07-05T02:15:48.510093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.08328","created_at":"2026-07-05T02:15:48.510093+00:00"},{"alias_kind":"pith_short_12","alias_value":"2PVEW54KT63C","created_at":"2026-07-05T02:15:48.510093+00:00"},{"alias_kind":"pith_short_16","alias_value":"2PVEW54KT63CS4XT","created_at":"2026-07-05T02:15:48.510093+00:00"},{"alias_kind":"pith_short_8","alias_value":"2PVEW54K","created_at":"2026-07-05T02:15:48.510093+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.14776","citing_title":"Script2Screen: Supporting Dialogue Scriptwriting with Interactive Audiovisual Generation","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2PVEW54KT63CS4XTVYQDQXJKA3","json":"https://pith.science/pith/2PVEW54KT63CS4XTVYQDQXJKA3.json","graph_json":"https://pith.science/api/pith-number/2PVEW54KT63CS4XTVYQDQXJKA3/graph.json","events_json":"https://pith.science/api/pith-number/2PVEW54KT63CS4XTVYQDQXJKA3/events.json","paper":"https://pith.science/paper/2PVEW54K"},"agent_actions":{"view_html":"https://pith.science/pith/2PVEW54KT63CS4XTVYQDQXJKA3","download_json":"https://pith.science/pith/2PVEW54KT63CS4XTVYQDQXJKA3.json","view_paper":"https://pith.science/paper/2PVEW54K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.08328&json=true","fetch_graph":"https://pith.science/api/pith-number/2PVEW54KT63CS4XTVYQDQXJKA3/graph.json","fetch_events":"https://pith.science/api/pith-number/2PVEW54KT63CS4XTVYQDQXJKA3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2PVEW54KT63CS4XTVYQDQXJKA3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2PVEW54KT63CS4XTVYQDQXJKA3/action/storage_attestation","attest_author":"https://pith.science/pith/2PVEW54KT63CS4XTVYQDQXJKA3/action/author_attestation","sign_citation":"https://pith.science/pith/2PVEW54KT63CS4XTVYQDQXJKA3/action/citation_signature","submit_replication":"https://pith.science/pith/2PVEW54KT63CS4XTVYQDQXJKA3/action/replication_record"}},"created_at":"2026-07-05T02:15:48.510093+00:00","updated_at":"2026-07-05T02:15:48.510093+00:00"}