{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RLXFKZ353QOS5OIH22OBNYLGO6","short_pith_number":"pith:RLXFKZ35","schema_version":"1.0","canonical_sha256":"8aee55677ddc1d2eb907d69c16e16677a044b6e30ebe1e83e42ceda9f4a67647","source":{"kind":"arxiv","id":"2605.23593","version":1},"attestation_state":"computed","paper":{"title":"A study on weakly-supervised training approaches for phoneme-level pronunciation scoring","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Jazm\\'in Vidal, Luciana Ferrer","submitted_at":"2026-05-22T13:03:16Z","abstract_excerpt":"Phoneme-level computer-assisted pronunciation training systems typically rely on phoneme-level annotations, which are costly and scarce. In this work, we investigate whether phoneme-level mispronunciation information can be learned without phoneme-level supervision by exploiting higher-level pronunciation labels. Specifically, we study a weakly supervised setting in which models are trained using only utterance- or word-level pronunciation labels and analyze whether this supervision induces useful phoneme-level score predictions. We further consider a two-stage training scenario in which a mod"},"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":"2605.23593","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-22T13:03:16Z","cross_cats_sorted":[],"title_canon_sha256":"08b9da3599caf4dccd9028089a9bce9d4fe53054837bc42a8d92632bcea32775","abstract_canon_sha256":"7db7f672f54750cb05b9862546e773af1572659fbade2e5a48baa9e29db7ae10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:21.318641Z","signature_b64":"S5P1ULTSoQIQFcAlFiBVnPn2wII/qaeM0g8KVS6jGWiNYnitK3Xb6QL0I3orEhRKIMyY59db4EptEqgd0C1lBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8aee55677ddc1d2eb907d69c16e16677a044b6e30ebe1e83e42ceda9f4a67647","last_reissued_at":"2026-05-25T02:02:21.317868Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:21.317868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A study on weakly-supervised training approaches for phoneme-level pronunciation scoring","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Jazm\\'in Vidal, Luciana Ferrer","submitted_at":"2026-05-22T13:03:16Z","abstract_excerpt":"Phoneme-level computer-assisted pronunciation training systems typically rely on phoneme-level annotations, which are costly and scarce. In this work, we investigate whether phoneme-level mispronunciation information can be learned without phoneme-level supervision by exploiting higher-level pronunciation labels. Specifically, we study a weakly supervised setting in which models are trained using only utterance- or word-level pronunciation labels and analyze whether this supervision induces useful phoneme-level score predictions. We further consider a two-stage training scenario in which a mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23593","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/2605.23593/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":"2605.23593","created_at":"2026-05-25T02:02:21.317995+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23593v1","created_at":"2026-05-25T02:02:21.317995+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23593","created_at":"2026-05-25T02:02:21.317995+00:00"},{"alias_kind":"pith_short_12","alias_value":"RLXFKZ353QOS","created_at":"2026-05-25T02:02:21.317995+00:00"},{"alias_kind":"pith_short_16","alias_value":"RLXFKZ353QOS5OIH","created_at":"2026-05-25T02:02:21.317995+00:00"},{"alias_kind":"pith_short_8","alias_value":"RLXFKZ35","created_at":"2026-05-25T02:02:21.317995+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.23593","citing_title":"A study on weakly-supervised training approaches for phoneme-level pronunciation scoring","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RLXFKZ353QOS5OIH22OBNYLGO6","json":"https://pith.science/pith/RLXFKZ353QOS5OIH22OBNYLGO6.json","graph_json":"https://pith.science/api/pith-number/RLXFKZ353QOS5OIH22OBNYLGO6/graph.json","events_json":"https://pith.science/api/pith-number/RLXFKZ353QOS5OIH22OBNYLGO6/events.json","paper":"https://pith.science/paper/RLXFKZ35"},"agent_actions":{"view_html":"https://pith.science/pith/RLXFKZ353QOS5OIH22OBNYLGO6","download_json":"https://pith.science/pith/RLXFKZ353QOS5OIH22OBNYLGO6.json","view_paper":"https://pith.science/paper/RLXFKZ35","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23593&json=true","fetch_graph":"https://pith.science/api/pith-number/RLXFKZ353QOS5OIH22OBNYLGO6/graph.json","fetch_events":"https://pith.science/api/pith-number/RLXFKZ353QOS5OIH22OBNYLGO6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RLXFKZ353QOS5OIH22OBNYLGO6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RLXFKZ353QOS5OIH22OBNYLGO6/action/storage_attestation","attest_author":"https://pith.science/pith/RLXFKZ353QOS5OIH22OBNYLGO6/action/author_attestation","sign_citation":"https://pith.science/pith/RLXFKZ353QOS5OIH22OBNYLGO6/action/citation_signature","submit_replication":"https://pith.science/pith/RLXFKZ353QOS5OIH22OBNYLGO6/action/replication_record"}},"created_at":"2026-05-25T02:02:21.317995+00:00","updated_at":"2026-05-25T02:02:21.317995+00:00"}