{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YAYVVMU4SZC52MOPJ5FHRAMSQN","short_pith_number":"pith:YAYVVMU4","schema_version":"1.0","canonical_sha256":"c0315ab29c9645dd31cf4f4a788192837bf2d2774575d9ac945b26e7b2ca45d1","source":{"kind":"arxiv","id":"2305.19563","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Automatic Pronunciation Assessment","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hongfu Liu, Mingqian Shi, Ye Wang","submitted_at":"2023-05-31T05:17:17Z","abstract_excerpt":"Automatic Pronunciation Assessment (APA) is vital for computer-assisted language learning. Prior methods rely on annotated speech-text data to train Automatic Speech Recognition (ASR) models or speech-score data to train regression models. In this work, we propose a novel zero-shot APA method based on the pre-trained acoustic model, HuBERT. Our method involves encoding speech input and corrupting them via a masking module. We then employ the Transformer encoder and apply k-means clustering to obtain token sequences. Finally, a scoring module is designed to measure the number of wrongly recover"},"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":"2305.19563","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-05-31T05:17:17Z","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"f8e3293738bf257c4f94b495f115458cd49c661cc7f1ab9a3b502f1f2aee6a84","abstract_canon_sha256":"466e35319c45812a93a75f96bb8e3a564a9f131f9d7ef99e073e32a0a70c33d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:51.844206Z","signature_b64":"q4+tf2hIwasxqbCbAhqoEOAFuFDT99v7rrIbWk1VeN7KcZ1Enivg/w3jPoSjWUjTc0KmpOo+rOBxg2u8ZVI8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0315ab29c9645dd31cf4f4a788192837bf2d2774575d9ac945b26e7b2ca45d1","last_reissued_at":"2026-07-05T06:15:51.843814Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:51.843814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Automatic Pronunciation Assessment","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hongfu Liu, Mingqian Shi, Ye Wang","submitted_at":"2023-05-31T05:17:17Z","abstract_excerpt":"Automatic Pronunciation Assessment (APA) is vital for computer-assisted language learning. Prior methods rely on annotated speech-text data to train Automatic Speech Recognition (ASR) models or speech-score data to train regression models. In this work, we propose a novel zero-shot APA method based on the pre-trained acoustic model, HuBERT. Our method involves encoding speech input and corrupting them via a masking module. We then employ the Transformer encoder and apply k-means clustering to obtain token sequences. Finally, a scoring module is designed to measure the number of wrongly recover"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19563","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/2305.19563/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":"2305.19563","created_at":"2026-07-05T06:15:51.843862+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.19563v1","created_at":"2026-07-05T06:15:51.843862+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19563","created_at":"2026-07-05T06:15:51.843862+00:00"},{"alias_kind":"pith_short_12","alias_value":"YAYVVMU4SZC5","created_at":"2026-07-05T06:15:51.843862+00:00"},{"alias_kind":"pith_short_16","alias_value":"YAYVVMU4SZC52MOP","created_at":"2026-07-05T06:15:51.843862+00:00"},{"alias_kind":"pith_short_8","alias_value":"YAYVVMU4","created_at":"2026-07-05T06:15:51.843862+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19910","citing_title":"Light-weight Pronunciation Assessment via Discrete Speech Token Surprisal","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YAYVVMU4SZC52MOPJ5FHRAMSQN","json":"https://pith.science/pith/YAYVVMU4SZC52MOPJ5FHRAMSQN.json","graph_json":"https://pith.science/api/pith-number/YAYVVMU4SZC52MOPJ5FHRAMSQN/graph.json","events_json":"https://pith.science/api/pith-number/YAYVVMU4SZC52MOPJ5FHRAMSQN/events.json","paper":"https://pith.science/paper/YAYVVMU4"},"agent_actions":{"view_html":"https://pith.science/pith/YAYVVMU4SZC52MOPJ5FHRAMSQN","download_json":"https://pith.science/pith/YAYVVMU4SZC52MOPJ5FHRAMSQN.json","view_paper":"https://pith.science/paper/YAYVVMU4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.19563&json=true","fetch_graph":"https://pith.science/api/pith-number/YAYVVMU4SZC52MOPJ5FHRAMSQN/graph.json","fetch_events":"https://pith.science/api/pith-number/YAYVVMU4SZC52MOPJ5FHRAMSQN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YAYVVMU4SZC52MOPJ5FHRAMSQN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YAYVVMU4SZC52MOPJ5FHRAMSQN/action/storage_attestation","attest_author":"https://pith.science/pith/YAYVVMU4SZC52MOPJ5FHRAMSQN/action/author_attestation","sign_citation":"https://pith.science/pith/YAYVVMU4SZC52MOPJ5FHRAMSQN/action/citation_signature","submit_replication":"https://pith.science/pith/YAYVVMU4SZC52MOPJ5FHRAMSQN/action/replication_record"}},"created_at":"2026-07-05T06:15:51.843862+00:00","updated_at":"2026-07-05T06:15:51.843862+00:00"}