{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EPUN7MMZ3QQ5VLN3ATEBZKVWT7","short_pith_number":"pith:EPUN7MMZ","schema_version":"1.0","canonical_sha256":"23e8dfb199dc21daadbb04c81caab69fc771406e24a90ad115e3ba099ccf814b","source":{"kind":"arxiv","id":"2408.13608","version":1},"attestation_state":"computed","paper":{"title":"SpeechCraft: A Fine-grained Expressive Speech Dataset with Natural Language Description","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.MM","authors_text":"Jia Jia, Kehan Li, Qixin Wang, Shuoyi Zhou, Songtao Zhou, Xiaoyu Qin, Zeyu Jin, Zhiyong Wu","submitted_at":"2024-08-24T15:36:08Z","abstract_excerpt":"Speech-language multi-modal learning presents a significant challenge due to the fine nuanced information inherent in speech styles. Therefore, a large-scale dataset providing elaborate comprehension of speech style is urgently needed to facilitate insightful interplay between speech audio and natural language. However, constructing such datasets presents a major trade-off between large-scale data collection and high-quality annotation. To tackle this challenge, we propose an automatic speech annotation system for expressiveness interpretation that annotates in-the-wild speech clips with expre"},"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":"2408.13608","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-08-24T15:36:08Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ae1de13dafb47c1081d3e436b6f4e45bd66ea68d18953da18d235e2d3382f309","abstract_canon_sha256":"d7001cbbabbb1f990f45a5cf5cefdf134feac67c16aab32965080d8312d62d2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:53.641194Z","signature_b64":"4M36YDMIh838kpljc7vN6rR6GdmPBrgTJRrWiakc0TPr6FqvMUbv1xqp7dEz5pTqHKeWBhuTDPuUZDwjvmJlCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23e8dfb199dc21daadbb04c81caab69fc771406e24a90ad115e3ba099ccf814b","last_reissued_at":"2026-07-05T08:59:53.640736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:53.640736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpeechCraft: A Fine-grained Expressive Speech Dataset with Natural Language Description","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.MM","authors_text":"Jia Jia, Kehan Li, Qixin Wang, Shuoyi Zhou, Songtao Zhou, Xiaoyu Qin, Zeyu Jin, Zhiyong Wu","submitted_at":"2024-08-24T15:36:08Z","abstract_excerpt":"Speech-language multi-modal learning presents a significant challenge due to the fine nuanced information inherent in speech styles. Therefore, a large-scale dataset providing elaborate comprehension of speech style is urgently needed to facilitate insightful interplay between speech audio and natural language. However, constructing such datasets presents a major trade-off between large-scale data collection and high-quality annotation. To tackle this challenge, we propose an automatic speech annotation system for expressiveness interpretation that annotates in-the-wild speech clips with expre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13608","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/2408.13608/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":"2408.13608","created_at":"2026-07-05T08:59:53.640798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.13608v1","created_at":"2026-07-05T08:59:53.640798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13608","created_at":"2026-07-05T08:59:53.640798+00:00"},{"alias_kind":"pith_short_12","alias_value":"EPUN7MMZ3QQ5","created_at":"2026-07-05T08:59:53.640798+00:00"},{"alias_kind":"pith_short_16","alias_value":"EPUN7MMZ3QQ5VLN3","created_at":"2026-07-05T08:59:53.640798+00:00"},{"alias_kind":"pith_short_8","alias_value":"EPUN7MMZ","created_at":"2026-07-05T08:59:53.640798+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03283","citing_title":"SpeakerCard-1M: An Evidence-Grounded Corpus for In-the-Wild Speaker Verification","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21164","citing_title":"MAGIC-TTS: Fine-Grained Controllable Speech Synthesis with Explicit Local Duration and Pause Control","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EPUN7MMZ3QQ5VLN3ATEBZKVWT7","json":"https://pith.science/pith/EPUN7MMZ3QQ5VLN3ATEBZKVWT7.json","graph_json":"https://pith.science/api/pith-number/EPUN7MMZ3QQ5VLN3ATEBZKVWT7/graph.json","events_json":"https://pith.science/api/pith-number/EPUN7MMZ3QQ5VLN3ATEBZKVWT7/events.json","paper":"https://pith.science/paper/EPUN7MMZ"},"agent_actions":{"view_html":"https://pith.science/pith/EPUN7MMZ3QQ5VLN3ATEBZKVWT7","download_json":"https://pith.science/pith/EPUN7MMZ3QQ5VLN3ATEBZKVWT7.json","view_paper":"https://pith.science/paper/EPUN7MMZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.13608&json=true","fetch_graph":"https://pith.science/api/pith-number/EPUN7MMZ3QQ5VLN3ATEBZKVWT7/graph.json","fetch_events":"https://pith.science/api/pith-number/EPUN7MMZ3QQ5VLN3ATEBZKVWT7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EPUN7MMZ3QQ5VLN3ATEBZKVWT7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EPUN7MMZ3QQ5VLN3ATEBZKVWT7/action/storage_attestation","attest_author":"https://pith.science/pith/EPUN7MMZ3QQ5VLN3ATEBZKVWT7/action/author_attestation","sign_citation":"https://pith.science/pith/EPUN7MMZ3QQ5VLN3ATEBZKVWT7/action/citation_signature","submit_replication":"https://pith.science/pith/EPUN7MMZ3QQ5VLN3ATEBZKVWT7/action/replication_record"}},"created_at":"2026-07-05T08:59:53.640798+00:00","updated_at":"2026-07-05T08:59:53.640798+00:00"}