{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z3H7OL2CNQZDSI436LQ3J4N2BE","short_pith_number":"pith:Z3H7OL2C","schema_version":"1.0","canonical_sha256":"cecff72f426c3239239bf2e1b4f1ba090cf077dcf0e70a7762962a66bd77f1e4","source":{"kind":"arxiv","id":"2505.24304","version":1},"attestation_state":"computed","paper":{"title":"A Perception-Based L2 Speech Intelligibility Indicator: Leveraging a Rater's Shadowing and Sequence-to-sequence Voice Conversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Daisuke Saito, Haopeng Geng, Nobuaki Minematsu","submitted_at":"2025-05-30T07:35:40Z","abstract_excerpt":"Evaluating L2 speech intelligibility is crucial for effective computer-assisted language learning (CALL). Conventional ASR-based methods often focus on native-likeness, which may fail to capture the actual intelligibility perceived by human listeners. In contrast, our work introduces a novel, perception based L2 speech intelligibility indicator that leverages a native rater's shadowing data within a sequence-to-sequence (seq2seq) voice conversion framework. By integrating an alignment mechanism and acoustic feature reconstruction, our approach simulates the auditory perception of native listen"},"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":"2505.24304","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-30T07:35:40Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"f00ad803d4e5fa98fb36ccfce5cfc01bc60ac7911cad4905589396161093997f","abstract_canon_sha256":"6dd19739a3382e769e760398c4098be0263f3b4668d376b7b3d97d4b91e289bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:46.416660Z","signature_b64":"NZ8hnmurOwOAn/OfJjFt1c76OYeWxELwhdpmX4geUINjAoTVQT6XdkgB+5h5K7u2fNtEWWMWKgdHdKPqDoBeDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cecff72f426c3239239bf2e1b4f1ba090cf077dcf0e70a7762962a66bd77f1e4","last_reissued_at":"2026-07-05T11:12:46.416099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:46.416099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Perception-Based L2 Speech Intelligibility Indicator: Leveraging a Rater's Shadowing and Sequence-to-sequence Voice Conversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Daisuke Saito, Haopeng Geng, Nobuaki Minematsu","submitted_at":"2025-05-30T07:35:40Z","abstract_excerpt":"Evaluating L2 speech intelligibility is crucial for effective computer-assisted language learning (CALL). Conventional ASR-based methods often focus on native-likeness, which may fail to capture the actual intelligibility perceived by human listeners. In contrast, our work introduces a novel, perception based L2 speech intelligibility indicator that leverages a native rater's shadowing data within a sequence-to-sequence (seq2seq) voice conversion framework. By integrating an alignment mechanism and acoustic feature reconstruction, our approach simulates the auditory perception of native listen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24304","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/2505.24304/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":"2505.24304","created_at":"2026-07-05T11:12:46.416161+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24304v1","created_at":"2026-07-05T11:12:46.416161+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24304","created_at":"2026-07-05T11:12:46.416161+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z3H7OL2CNQZD","created_at":"2026-07-05T11:12:46.416161+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z3H7OL2CNQZDSI43","created_at":"2026-07-05T11:12:46.416161+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z3H7OL2C","created_at":"2026-07-05T11:12:46.416161+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24304","citing_title":"A Perception-Based L2 Speech Intelligibility Indicator: Leveraging a Rater's Shadowing and Sequence-to-sequence Voice Conversion","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z3H7OL2CNQZDSI436LQ3J4N2BE","json":"https://pith.science/pith/Z3H7OL2CNQZDSI436LQ3J4N2BE.json","graph_json":"https://pith.science/api/pith-number/Z3H7OL2CNQZDSI436LQ3J4N2BE/graph.json","events_json":"https://pith.science/api/pith-number/Z3H7OL2CNQZDSI436LQ3J4N2BE/events.json","paper":"https://pith.science/paper/Z3H7OL2C"},"agent_actions":{"view_html":"https://pith.science/pith/Z3H7OL2CNQZDSI436LQ3J4N2BE","download_json":"https://pith.science/pith/Z3H7OL2CNQZDSI436LQ3J4N2BE.json","view_paper":"https://pith.science/paper/Z3H7OL2C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24304&json=true","fetch_graph":"https://pith.science/api/pith-number/Z3H7OL2CNQZDSI436LQ3J4N2BE/graph.json","fetch_events":"https://pith.science/api/pith-number/Z3H7OL2CNQZDSI436LQ3J4N2BE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z3H7OL2CNQZDSI436LQ3J4N2BE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z3H7OL2CNQZDSI436LQ3J4N2BE/action/storage_attestation","attest_author":"https://pith.science/pith/Z3H7OL2CNQZDSI436LQ3J4N2BE/action/author_attestation","sign_citation":"https://pith.science/pith/Z3H7OL2CNQZDSI436LQ3J4N2BE/action/citation_signature","submit_replication":"https://pith.science/pith/Z3H7OL2CNQZDSI436LQ3J4N2BE/action/replication_record"}},"created_at":"2026-07-05T11:12:46.416161+00:00","updated_at":"2026-07-05T11:12:46.416161+00:00"}