{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P7ZGF6IVSHKZGGEPXDE5TDCZ7V","short_pith_number":"pith:P7ZGF6IV","schema_version":"1.0","canonical_sha256":"7ff262f91591d593188fb8c9d98c59fd74d542217156691e6b679dc625ee6088","source":{"kind":"arxiv","id":"2406.07256","version":1},"attestation_state":"computed","paper":{"title":"AS-70: A Mandarin stuttered speech dataset for automatic speech recognition and stuttering event detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Binbin Zhang, Hongfei Xue, Hui Bu, Jia Bin, Jiaming Zhou, Jun Du, Lei Xie, Lezhi Wang, Ming Li, Qisheng Li, Rong Gong, Shaomei Wu, Xin Xu, Yong Qin","submitted_at":"2024-06-11T13:35:50Z","abstract_excerpt":"The rapid advancements in speech technologies over the past two decades have led to human-level performance in tasks like automatic speech recognition (ASR) for fluent speech. However, the efficacy of these models diminishes when applied to atypical speech, such as stuttering. This paper introduces AS-70, the first publicly available Mandarin stuttered speech dataset, which stands out as the largest dataset in its category. Encompassing conversational and voice command reading speech, AS-70 includes verbatim manual transcription, rendering it suitable for various speech-related tasks. Furtherm"},"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":"2406.07256","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-11T13:35:50Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"161b34a2ccdc4f22adb3ea2804719e080ce1c9c95407ad90f7466d9ff7163193","abstract_canon_sha256":"95a8af6167fdfa27c06848b6f49cff54a9922e50723ab77de88af1625001d2f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:20.715655Z","signature_b64":"PUz7zzIBmWEsAp885N5VHubAum1vFjeKEjB0DWD+BHQ+PtNxRpsjG4WjHX45owYS8Rpt+rRkp+trj18Eh8AoCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ff262f91591d593188fb8c9d98c59fd74d542217156691e6b679dc625ee6088","last_reissued_at":"2026-07-05T08:30:20.715075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:20.715075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AS-70: A Mandarin stuttered speech dataset for automatic speech recognition and stuttering event detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Binbin Zhang, Hongfei Xue, Hui Bu, Jia Bin, Jiaming Zhou, Jun Du, Lei Xie, Lezhi Wang, Ming Li, Qisheng Li, Rong Gong, Shaomei Wu, Xin Xu, Yong Qin","submitted_at":"2024-06-11T13:35:50Z","abstract_excerpt":"The rapid advancements in speech technologies over the past two decades have led to human-level performance in tasks like automatic speech recognition (ASR) for fluent speech. However, the efficacy of these models diminishes when applied to atypical speech, such as stuttering. This paper introduces AS-70, the first publicly available Mandarin stuttered speech dataset, which stands out as the largest dataset in its category. Encompassing conversational and voice command reading speech, AS-70 includes verbatim manual transcription, rendering it suitable for various speech-related tasks. Furtherm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07256","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/2406.07256/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":"2406.07256","created_at":"2026-07-05T08:30:20.715142+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07256v1","created_at":"2026-07-05T08:30:20.715142+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07256","created_at":"2026-07-05T08:30:20.715142+00:00"},{"alias_kind":"pith_short_12","alias_value":"P7ZGF6IVSHKZ","created_at":"2026-07-05T08:30:20.715142+00:00"},{"alias_kind":"pith_short_16","alias_value":"P7ZGF6IVSHKZGGEP","created_at":"2026-07-05T08:30:20.715142+00:00"},{"alias_kind":"pith_short_8","alias_value":"P7ZGF6IV","created_at":"2026-07-05T08:30:20.715142+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21457","citing_title":"DisSpeech: Low-Resource Controllable Mandarin Stuttered Speech Synthesis for ASR Augmentation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02080","citing_title":"Cripping AI: Reimagining AI Through Lived Disability Experiences","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P7ZGF6IVSHKZGGEPXDE5TDCZ7V","json":"https://pith.science/pith/P7ZGF6IVSHKZGGEPXDE5TDCZ7V.json","graph_json":"https://pith.science/api/pith-number/P7ZGF6IVSHKZGGEPXDE5TDCZ7V/graph.json","events_json":"https://pith.science/api/pith-number/P7ZGF6IVSHKZGGEPXDE5TDCZ7V/events.json","paper":"https://pith.science/paper/P7ZGF6IV"},"agent_actions":{"view_html":"https://pith.science/pith/P7ZGF6IVSHKZGGEPXDE5TDCZ7V","download_json":"https://pith.science/pith/P7ZGF6IVSHKZGGEPXDE5TDCZ7V.json","view_paper":"https://pith.science/paper/P7ZGF6IV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07256&json=true","fetch_graph":"https://pith.science/api/pith-number/P7ZGF6IVSHKZGGEPXDE5TDCZ7V/graph.json","fetch_events":"https://pith.science/api/pith-number/P7ZGF6IVSHKZGGEPXDE5TDCZ7V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P7ZGF6IVSHKZGGEPXDE5TDCZ7V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P7ZGF6IVSHKZGGEPXDE5TDCZ7V/action/storage_attestation","attest_author":"https://pith.science/pith/P7ZGF6IVSHKZGGEPXDE5TDCZ7V/action/author_attestation","sign_citation":"https://pith.science/pith/P7ZGF6IVSHKZGGEPXDE5TDCZ7V/action/citation_signature","submit_replication":"https://pith.science/pith/P7ZGF6IVSHKZGGEPXDE5TDCZ7V/action/replication_record"}},"created_at":"2026-07-05T08:30:20.715142+00:00","updated_at":"2026-07-05T08:30:20.715142+00:00"}