{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CG4Q5EC4LKNBAJQXTFX3S5MNOY","short_pith_number":"pith:CG4Q5EC4","schema_version":"1.0","canonical_sha256":"11b90e905c5a9a102617996fb9758d7637f2d2972c87be94132c669602e2f1ff","source":{"kind":"arxiv","id":"2505.16182","version":1},"attestation_state":"computed","paper":{"title":"Discrete Tokens Exhibit Interlanguage Speech Intelligibility Benefit: an Analytical Study Towards Accent-robust ASR Only with Native Speech Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Daisuke Saito, Keisuke Imoto, Kentaro Onda, Nobuaki Minematsu, Satoru Fukayama","submitted_at":"2025-05-22T03:36:28Z","abstract_excerpt":"In this study, we gained insight that contributes to achieving accent-robust ASR using only native speech data. In human perception of non-native speech, the phenomenon known as \"interlanguage speech intelligibility benefit\" (ISIB) is observed, where non-native listeners who share the native language with the speaker understand the speech better compared even to native listeners. Based on the idea that discrete tokens extracted from self-supervised learning (SSL) models represent the human perception of speech, we conducted an analytical study on the robustness of discrete token-based ASR to n"},"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":"2505.16182","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-22T03:36:28Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"3ab0047be6140b23e485044482e6bc7711a008e100e9a8cce2dcf042df661efd","abstract_canon_sha256":"889792a0d1d148cdbf33a3766ce0a9046c729a1953f5cc92949457b02f08c130"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:31.280120Z","signature_b64":"Rjcz895feWZGp2PVyKWkHnys6qQXbQhfVxQ/FOiOUkgcxbibRiObEFsF55MF4o35C3eyFvUGtcyPT34e7KkZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11b90e905c5a9a102617996fb9758d7637f2d2972c87be94132c669602e2f1ff","last_reissued_at":"2026-07-05T11:07:31.279604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:31.279604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discrete Tokens Exhibit Interlanguage Speech Intelligibility Benefit: an Analytical Study Towards Accent-robust ASR Only with Native Speech Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Daisuke Saito, Keisuke Imoto, Kentaro Onda, Nobuaki Minematsu, Satoru Fukayama","submitted_at":"2025-05-22T03:36:28Z","abstract_excerpt":"In this study, we gained insight that contributes to achieving accent-robust ASR using only native speech data. In human perception of non-native speech, the phenomenon known as \"interlanguage speech intelligibility benefit\" (ISIB) is observed, where non-native listeners who share the native language with the speaker understand the speech better compared even to native listeners. Based on the idea that discrete tokens extracted from self-supervised learning (SSL) models represent the human perception of speech, we conducted an analytical study on the robustness of discrete token-based ASR to n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16182","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/2505.16182/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":"2505.16182","created_at":"2026-07-05T11:07:31.279668+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16182v1","created_at":"2026-07-05T11:07:31.279668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16182","created_at":"2026-07-05T11:07:31.279668+00:00"},{"alias_kind":"pith_short_12","alias_value":"CG4Q5EC4LKNB","created_at":"2026-07-05T11:07:31.279668+00:00"},{"alias_kind":"pith_short_16","alias_value":"CG4Q5EC4LKNBAJQX","created_at":"2026-07-05T11:07:31.279668+00:00"},{"alias_kind":"pith_short_8","alias_value":"CG4Q5EC4","created_at":"2026-07-05T11:07:31.279668+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16182","citing_title":"Discrete Tokens Exhibit Interlanguage Speech Intelligibility Benefit: an Analytical Study Towards Accent-robust ASR Only with Native Speech Data","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CG4Q5EC4LKNBAJQXTFX3S5MNOY","json":"https://pith.science/pith/CG4Q5EC4LKNBAJQXTFX3S5MNOY.json","graph_json":"https://pith.science/api/pith-number/CG4Q5EC4LKNBAJQXTFX3S5MNOY/graph.json","events_json":"https://pith.science/api/pith-number/CG4Q5EC4LKNBAJQXTFX3S5MNOY/events.json","paper":"https://pith.science/paper/CG4Q5EC4"},"agent_actions":{"view_html":"https://pith.science/pith/CG4Q5EC4LKNBAJQXTFX3S5MNOY","download_json":"https://pith.science/pith/CG4Q5EC4LKNBAJQXTFX3S5MNOY.json","view_paper":"https://pith.science/paper/CG4Q5EC4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16182&json=true","fetch_graph":"https://pith.science/api/pith-number/CG4Q5EC4LKNBAJQXTFX3S5MNOY/graph.json","fetch_events":"https://pith.science/api/pith-number/CG4Q5EC4LKNBAJQXTFX3S5MNOY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CG4Q5EC4LKNBAJQXTFX3S5MNOY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CG4Q5EC4LKNBAJQXTFX3S5MNOY/action/storage_attestation","attest_author":"https://pith.science/pith/CG4Q5EC4LKNBAJQXTFX3S5MNOY/action/author_attestation","sign_citation":"https://pith.science/pith/CG4Q5EC4LKNBAJQXTFX3S5MNOY/action/citation_signature","submit_replication":"https://pith.science/pith/CG4Q5EC4LKNBAJQXTFX3S5MNOY/action/replication_record"}},"created_at":"2026-07-05T11:07:31.279668+00:00","updated_at":"2026-07-05T11:07:31.279668+00:00"}