{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P3AEW5EDJLAT4RP2W6SJTNCPNN","short_pith_number":"pith:P3AEW5ED","schema_version":"1.0","canonical_sha256":"7ec04b74834ac13e45fab7a499b44f6b74ee93362f777436ac62b1ebe115b2c2","source":{"kind":"arxiv","id":"2603.14275","version":2},"attestation_state":"computed","paper":{"title":"Controllable Accent Normalization via Discrete Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Haizhou Li, Qibing Bai, Shuai Wang, Tom Ko, Yannan Wang, Yuhan Du","submitted_at":"2026-03-15T08:17:25Z","abstract_excerpt":"Existing accent normalization methods do not typically offer control over accent strength, yet many applications-such as language learning and dubbing-require tunable accent retention. We propose DLM-AN, a controllable accent normalization system built on masked discrete diffusion over self-supervised speech tokens. A Common Token Predictor identifies source tokens that likely encode native pronunciation; these tokens are selectively reused to initialize the reverse diffusion process. This provides a simple yet effective mechanism for controlling accent strength: reusing more tokens preserves "},"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":"2603.14275","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-03-15T08:17:25Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"9611cb97a900a56cac5276509bb6418d2ec1a38d74cfcafafb20d2bac2af5a88","abstract_canon_sha256":"37b9be858f06af439a0bd7bc641a86bbebe3a596bcc8878ae0f72c88d998fa47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:28.643411Z","signature_b64":"pcGxOdrvMx+nqs3CghlnbqZ8Lp6+9Si0OqYLP4EDnlbD9I8/ovFGaDTml8O8UOZs8iIq5Mq+dyNBmbNU6Z9wDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ec04b74834ac13e45fab7a499b44f6b74ee93362f777436ac62b1ebe115b2c2","last_reissued_at":"2026-06-23T03:14:28.642956Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:28.642956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controllable Accent Normalization via Discrete Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Haizhou Li, Qibing Bai, Shuai Wang, Tom Ko, Yannan Wang, Yuhan Du","submitted_at":"2026-03-15T08:17:25Z","abstract_excerpt":"Existing accent normalization methods do not typically offer control over accent strength, yet many applications-such as language learning and dubbing-require tunable accent retention. We propose DLM-AN, a controllable accent normalization system built on masked discrete diffusion over self-supervised speech tokens. A Common Token Predictor identifies source tokens that likely encode native pronunciation; these tokens are selectively reused to initialize the reverse diffusion process. This provides a simple yet effective mechanism for controlling accent strength: reusing more tokens preserves "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.14275","kind":"arxiv","version":2},"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/2603.14275/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":"2603.14275","created_at":"2026-06-23T03:14:28.643014+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.14275v2","created_at":"2026-06-23T03:14:28.643014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.14275","created_at":"2026-06-23T03:14:28.643014+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3AEW5EDJLAT","created_at":"2026-06-23T03:14:28.643014+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3AEW5EDJLAT4RP2","created_at":"2026-06-23T03:14:28.643014+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3AEW5ED","created_at":"2026-06-23T03:14:28.643014+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.27281","citing_title":"Accent Conversion: A Problem-Driven Survey of Sociolinguistic and Technical Constraints","ref_index":76,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P3AEW5EDJLAT4RP2W6SJTNCPNN","json":"https://pith.science/pith/P3AEW5EDJLAT4RP2W6SJTNCPNN.json","graph_json":"https://pith.science/api/pith-number/P3AEW5EDJLAT4RP2W6SJTNCPNN/graph.json","events_json":"https://pith.science/api/pith-number/P3AEW5EDJLAT4RP2W6SJTNCPNN/events.json","paper":"https://pith.science/paper/P3AEW5ED"},"agent_actions":{"view_html":"https://pith.science/pith/P3AEW5EDJLAT4RP2W6SJTNCPNN","download_json":"https://pith.science/pith/P3AEW5EDJLAT4RP2W6SJTNCPNN.json","view_paper":"https://pith.science/paper/P3AEW5ED","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.14275&json=true","fetch_graph":"https://pith.science/api/pith-number/P3AEW5EDJLAT4RP2W6SJTNCPNN/graph.json","fetch_events":"https://pith.science/api/pith-number/P3AEW5EDJLAT4RP2W6SJTNCPNN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3AEW5EDJLAT4RP2W6SJTNCPNN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3AEW5EDJLAT4RP2W6SJTNCPNN/action/storage_attestation","attest_author":"https://pith.science/pith/P3AEW5EDJLAT4RP2W6SJTNCPNN/action/author_attestation","sign_citation":"https://pith.science/pith/P3AEW5EDJLAT4RP2W6SJTNCPNN/action/citation_signature","submit_replication":"https://pith.science/pith/P3AEW5EDJLAT4RP2W6SJTNCPNN/action/replication_record"}},"created_at":"2026-06-23T03:14:28.643014+00:00","updated_at":"2026-06-23T03:14:28.643014+00:00"}