{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JZ7JARDE52TSAXIK3HZ2NPEEOB","short_pith_number":"pith:JZ7JARDE","schema_version":"1.0","canonical_sha256":"4e7e904464eea7205d0ad9f3a6bc84704fdd2d7e724326605c5b0c6815714b37","source":{"kind":"arxiv","id":"2305.11438","version":1},"attestation_state":"computed","paper":{"title":"Phonetic and Prosody-aware Self-supervised Learning Approach for Non-native Fluency Scoring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Kaiqi Fu, Shaojun Gao, Shuju Shi, Wei Li, Xiaohai Tian, Zejun Ma","submitted_at":"2023-05-19T05:39:41Z","abstract_excerpt":"Speech fluency/disfluency can be evaluated by analyzing a range of phonetic and prosodic features. Deep neural networks are commonly trained to map fluency-related features into the human scores. However, the effectiveness of deep learning-based models is constrained by the limited amount of labeled training samples. To address this, we introduce a self-supervised learning (SSL) approach that takes into account phonetic and prosody awareness for fluency scoring. Specifically, we first pre-train the model using a reconstruction loss function, by masking phones and their durations jointly on a l"},"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":"2305.11438","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T05:39:41Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"8af8b5495643ddadd283a31ed546b8e67bf5261859714e1c792c65a03a60269f","abstract_canon_sha256":"421234b84d536eb2270e2f34e44f42ca7f4337ad2dd5fa24ffcee6b3b8579a5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:46.953518Z","signature_b64":"KHjolepyM98+3uyCufrS4adBqacb1lg2rdJiqZ/PVjiR/BzCdchZfh3y/pJfT4xs0pa0ETfvOuJ8bw+GfyPsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e7e904464eea7205d0ad9f3a6bc84704fdd2d7e724326605c5b0c6815714b37","last_reissued_at":"2026-07-05T06:11:46.953162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:46.953162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Phonetic and Prosody-aware Self-supervised Learning Approach for Non-native Fluency Scoring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Kaiqi Fu, Shaojun Gao, Shuju Shi, Wei Li, Xiaohai Tian, Zejun Ma","submitted_at":"2023-05-19T05:39:41Z","abstract_excerpt":"Speech fluency/disfluency can be evaluated by analyzing a range of phonetic and prosodic features. Deep neural networks are commonly trained to map fluency-related features into the human scores. However, the effectiveness of deep learning-based models is constrained by the limited amount of labeled training samples. To address this, we introduce a self-supervised learning (SSL) approach that takes into account phonetic and prosody awareness for fluency scoring. Specifically, we first pre-train the model using a reconstruction loss function, by masking phones and their durations jointly on a l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11438","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/2305.11438/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":"2305.11438","created_at":"2026-07-05T06:11:46.953223+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11438v1","created_at":"2026-07-05T06:11:46.953223+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11438","created_at":"2026-07-05T06:11:46.953223+00:00"},{"alias_kind":"pith_short_12","alias_value":"JZ7JARDE52TS","created_at":"2026-07-05T06:11:46.953223+00:00"},{"alias_kind":"pith_short_16","alias_value":"JZ7JARDE52TSAXIK","created_at":"2026-07-05T06:11:46.953223+00:00"},{"alias_kind":"pith_short_8","alias_value":"JZ7JARDE","created_at":"2026-07-05T06:11:46.953223+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JZ7JARDE52TSAXIK3HZ2NPEEOB","json":"https://pith.science/pith/JZ7JARDE52TSAXIK3HZ2NPEEOB.json","graph_json":"https://pith.science/api/pith-number/JZ7JARDE52TSAXIK3HZ2NPEEOB/graph.json","events_json":"https://pith.science/api/pith-number/JZ7JARDE52TSAXIK3HZ2NPEEOB/events.json","paper":"https://pith.science/paper/JZ7JARDE"},"agent_actions":{"view_html":"https://pith.science/pith/JZ7JARDE52TSAXIK3HZ2NPEEOB","download_json":"https://pith.science/pith/JZ7JARDE52TSAXIK3HZ2NPEEOB.json","view_paper":"https://pith.science/paper/JZ7JARDE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11438&json=true","fetch_graph":"https://pith.science/api/pith-number/JZ7JARDE52TSAXIK3HZ2NPEEOB/graph.json","fetch_events":"https://pith.science/api/pith-number/JZ7JARDE52TSAXIK3HZ2NPEEOB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JZ7JARDE52TSAXIK3HZ2NPEEOB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JZ7JARDE52TSAXIK3HZ2NPEEOB/action/storage_attestation","attest_author":"https://pith.science/pith/JZ7JARDE52TSAXIK3HZ2NPEEOB/action/author_attestation","sign_citation":"https://pith.science/pith/JZ7JARDE52TSAXIK3HZ2NPEEOB/action/citation_signature","submit_replication":"https://pith.science/pith/JZ7JARDE52TSAXIK3HZ2NPEEOB/action/replication_record"}},"created_at":"2026-07-05T06:11:46.953223+00:00","updated_at":"2026-07-05T06:11:46.953223+00:00"}