{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GGSTXJFA2HDL55UKDW6LA4EHOP","short_pith_number":"pith:GGSTXJFA","schema_version":"1.0","canonical_sha256":"31a53ba4a0d1c6bef68a1dbcb0708773d67b74282326780d36a94ffad710dd29","source":{"kind":"arxiv","id":"2506.07646","version":1},"attestation_state":"computed","paper":{"title":"Transcript-Prompted Whisper with Dictionary-Enhanced Decoding for Japanese Speech Annotation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jiawang Liu, Rui Hu, Shixi Huang, Xiaolong Lin, Zhenpeng Zhan","submitted_at":"2025-06-09T11:10:24Z","abstract_excerpt":"In this paper, we propose a method for annotating phonemic and prosodic labels on a given audio-transcript pair, aimed at constructing Japanese text-to-speech (TTS) datasets. Our approach involves fine-tuning a large-scale pre-trained automatic speech recognition (ASR) model, conditioned on ground truth transcripts, to simultaneously output phrase-level graphemes and annotation labels. To further correct errors in phonemic labeling, we employ a decoding strategy that utilizes dictionary prior knowledge. The objective evaluation results demonstrate that our proposed method outperforms previous "},"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":"2506.07646","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T11:10:24Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"5996603ada569f71d51ad885f93dc901ad4e55e576b9db2de7422330c074b9ba","abstract_canon_sha256":"118f3f161395528b995bddc1dbb6d3cb6ef53badbda514bc0b5e858b43e5adab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:30.935797Z","signature_b64":"T9ZsrpeCkaF760P4KMAk6u5OoUUv7JyuUAUEp+iKMeH+z7Pf0feyA+01F9BHwsFcRj/ujhEArJcprLgaPer5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31a53ba4a0d1c6bef68a1dbcb0708773d67b74282326780d36a94ffad710dd29","last_reissued_at":"2026-07-05T11:18:30.935302Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:30.935302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transcript-Prompted Whisper with Dictionary-Enhanced Decoding for Japanese Speech Annotation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jiawang Liu, Rui Hu, Shixi Huang, Xiaolong Lin, Zhenpeng Zhan","submitted_at":"2025-06-09T11:10:24Z","abstract_excerpt":"In this paper, we propose a method for annotating phonemic and prosodic labels on a given audio-transcript pair, aimed at constructing Japanese text-to-speech (TTS) datasets. Our approach involves fine-tuning a large-scale pre-trained automatic speech recognition (ASR) model, conditioned on ground truth transcripts, to simultaneously output phrase-level graphemes and annotation labels. To further correct errors in phonemic labeling, we employ a decoding strategy that utilizes dictionary prior knowledge. The objective evaluation results demonstrate that our proposed method outperforms previous "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07646","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/2506.07646/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":"2506.07646","created_at":"2026-07-05T11:18:30.935370+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07646v1","created_at":"2026-07-05T11:18:30.935370+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07646","created_at":"2026-07-05T11:18:30.935370+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGSTXJFA2HDL","created_at":"2026-07-05T11:18:30.935370+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGSTXJFA2HDL55UK","created_at":"2026-07-05T11:18:30.935370+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGSTXJFA","created_at":"2026-07-05T11:18:30.935370+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07646","citing_title":"Transcript-Prompted Whisper with Dictionary-Enhanced Decoding for Japanese Speech Annotation","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GGSTXJFA2HDL55UKDW6LA4EHOP","json":"https://pith.science/pith/GGSTXJFA2HDL55UKDW6LA4EHOP.json","graph_json":"https://pith.science/api/pith-number/GGSTXJFA2HDL55UKDW6LA4EHOP/graph.json","events_json":"https://pith.science/api/pith-number/GGSTXJFA2HDL55UKDW6LA4EHOP/events.json","paper":"https://pith.science/paper/GGSTXJFA"},"agent_actions":{"view_html":"https://pith.science/pith/GGSTXJFA2HDL55UKDW6LA4EHOP","download_json":"https://pith.science/pith/GGSTXJFA2HDL55UKDW6LA4EHOP.json","view_paper":"https://pith.science/paper/GGSTXJFA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07646&json=true","fetch_graph":"https://pith.science/api/pith-number/GGSTXJFA2HDL55UKDW6LA4EHOP/graph.json","fetch_events":"https://pith.science/api/pith-number/GGSTXJFA2HDL55UKDW6LA4EHOP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGSTXJFA2HDL55UKDW6LA4EHOP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGSTXJFA2HDL55UKDW6LA4EHOP/action/storage_attestation","attest_author":"https://pith.science/pith/GGSTXJFA2HDL55UKDW6LA4EHOP/action/author_attestation","sign_citation":"https://pith.science/pith/GGSTXJFA2HDL55UKDW6LA4EHOP/action/citation_signature","submit_replication":"https://pith.science/pith/GGSTXJFA2HDL55UKDW6LA4EHOP/action/replication_record"}},"created_at":"2026-07-05T11:18:30.935370+00:00","updated_at":"2026-07-05T11:18:30.935370+00:00"}