{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:I6WMFE4BKEP52QZ2HPD6FNSBZI","short_pith_number":"pith:I6WMFE4B","canonical_record":{"source":{"id":"2309.13994","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-25T09:51:59Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"f182833db1dd10f71898e58498bf4729e5d484e2c238276dadaef7eefbcec8ee","abstract_canon_sha256":"e99e90f4a955b8db3a703f71435e92090617fc21ecb47bbeca025ad548cd3936"},"schema_version":"1.0"},"canonical_sha256":"47acc29381511fdd433a3bc7e2b641ca398fe1e264ae32df822bd92cfc77968e","source":{"kind":"arxiv","id":"2309.13994","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.13994","created_at":"2026-07-05T10:09:40Z"},{"alias_kind":"arxiv_version","alias_value":"2309.13994v1","created_at":"2026-07-05T10:09:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13994","created_at":"2026-07-05T10:09:40Z"},{"alias_kind":"pith_short_12","alias_value":"I6WMFE4BKEP5","created_at":"2026-07-05T10:09:40Z"},{"alias_kind":"pith_short_16","alias_value":"I6WMFE4BKEP52QZ2","created_at":"2026-07-05T10:09:40Z"},{"alias_kind":"pith_short_8","alias_value":"I6WMFE4B","created_at":"2026-07-05T10:09:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:I6WMFE4BKEP52QZ2HPD6FNSBZI","target":"record","payload":{"canonical_record":{"source":{"id":"2309.13994","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-25T09:51:59Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"f182833db1dd10f71898e58498bf4729e5d484e2c238276dadaef7eefbcec8ee","abstract_canon_sha256":"e99e90f4a955b8db3a703f71435e92090617fc21ecb47bbeca025ad548cd3936"},"schema_version":"1.0"},"canonical_sha256":"47acc29381511fdd433a3bc7e2b641ca398fe1e264ae32df822bd92cfc77968e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:40.672663Z","signature_b64":"/flHTHcnXYhQ7t12uPWJGz+jAhuDFd1LsK4Xoubp0txNSeGnazEVTt9hl6RZvFv8bUpt0d4lUxumjQar66cKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47acc29381511fdd433a3bc7e2b641ca398fe1e264ae32df822bd92cfc77968e","last_reissued_at":"2026-07-05T10:09:40.672253Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:40.672253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.13994","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:09:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A1yzmk9bZK3ANB3Gax6tbBROL/QLbhCT8TnUcpdncq6F/g9b58RxRBLy0fNJXwEkR/86TUFvkzoH+xzM/XL5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T06:58:28.919557Z"},"content_sha256":"a6c4f501c187045e925b82c9f89dc63ec897308f15d7acdd2635ffc4246ce8fe","schema_version":"1.0","event_id":"sha256:a6c4f501c187045e925b82c9f89dc63ec897308f15d7acdd2635ffc4246ce8fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:I6WMFE4BKEP52QZ2HPD6FNSBZI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Accent Adaptation Through Masked Language Model Correction Of Discrete Self-Supervised Speech Units","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hugo Van hamme, Jakob Poncelet","submitted_at":"2023-09-25T09:51:59Z","abstract_excerpt":"Self-supervised pre-trained speech models have strongly improved speech recognition, yet they are still sensitive to domain shifts and accented or atypical speech. Many of these models rely on quantisation or clustering to learn discrete acoustic units. We propose to correct the discovered discrete units for accented speech back to a standard pronunciation in an unsupervised manner. A masked language model is trained on discrete units from a standard accent and iteratively corrects an accented token sequence by masking unexpected cluster sequences and predicting their common variant. Small acc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13994","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/2309.13994/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:09:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8W1BQ0MpYUAyNSyBjDJGTP7k2udqrqMkoWTs+SIVGgVmB/5sUUBOhpzWH0e9vNKFaUJNIdKidE7EUdUYc+cYBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T06:58:28.919938Z"},"content_sha256":"bbde2a3c5659fc7a794e13403469aaa49383b730b3ceed080de8b15ac24e9f98","schema_version":"1.0","event_id":"sha256:bbde2a3c5659fc7a794e13403469aaa49383b730b3ceed080de8b15ac24e9f98"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I6WMFE4BKEP52QZ2HPD6FNSBZI/bundle.json","state_url":"https://pith.science/pith/I6WMFE4BKEP52QZ2HPD6FNSBZI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I6WMFE4BKEP52QZ2HPD6FNSBZI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-13T06:58:28Z","links":{"resolver":"https://pith.science/pith/I6WMFE4BKEP52QZ2HPD6FNSBZI","bundle":"https://pith.science/pith/I6WMFE4BKEP52QZ2HPD6FNSBZI/bundle.json","state":"https://pith.science/pith/I6WMFE4BKEP52QZ2HPD6FNSBZI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I6WMFE4BKEP52QZ2HPD6FNSBZI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:I6WMFE4BKEP52QZ2HPD6FNSBZI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e99e90f4a955b8db3a703f71435e92090617fc21ecb47bbeca025ad548cd3936","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-25T09:51:59Z","title_canon_sha256":"f182833db1dd10f71898e58498bf4729e5d484e2c238276dadaef7eefbcec8ee"},"schema_version":"1.0","source":{"id":"2309.13994","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.13994","created_at":"2026-07-05T10:09:40Z"},{"alias_kind":"arxiv_version","alias_value":"2309.13994v1","created_at":"2026-07-05T10:09:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13994","created_at":"2026-07-05T10:09:40Z"},{"alias_kind":"pith_short_12","alias_value":"I6WMFE4BKEP5","created_at":"2026-07-05T10:09:40Z"},{"alias_kind":"pith_short_16","alias_value":"I6WMFE4BKEP52QZ2","created_at":"2026-07-05T10:09:40Z"},{"alias_kind":"pith_short_8","alias_value":"I6WMFE4B","created_at":"2026-07-05T10:09:40Z"}],"graph_snapshots":[{"event_id":"sha256:bbde2a3c5659fc7a794e13403469aaa49383b730b3ceed080de8b15ac24e9f98","target":"graph","created_at":"2026-07-05T10:09:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2309.13994/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised pre-trained speech models have strongly improved speech recognition, yet they are still sensitive to domain shifts and accented or atypical speech. Many of these models rely on quantisation or clustering to learn discrete acoustic units. We propose to correct the discovered discrete units for accented speech back to a standard pronunciation in an unsupervised manner. A masked language model is trained on discrete units from a standard accent and iteratively corrects an accented token sequence by masking unexpected cluster sequences and predicting their common variant. Small acc","authors_text":"Hugo Van hamme, Jakob Poncelet","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-25T09:51:59Z","title":"Unsupervised Accent Adaptation Through Masked Language Model Correction Of Discrete Self-Supervised Speech Units"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13994","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a6c4f501c187045e925b82c9f89dc63ec897308f15d7acdd2635ffc4246ce8fe","target":"record","created_at":"2026-07-05T10:09:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e99e90f4a955b8db3a703f71435e92090617fc21ecb47bbeca025ad548cd3936","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-25T09:51:59Z","title_canon_sha256":"f182833db1dd10f71898e58498bf4729e5d484e2c238276dadaef7eefbcec8ee"},"schema_version":"1.0","source":{"id":"2309.13994","kind":"arxiv","version":1}},"canonical_sha256":"47acc29381511fdd433a3bc7e2b641ca398fe1e264ae32df822bd92cfc77968e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47acc29381511fdd433a3bc7e2b641ca398fe1e264ae32df822bd92cfc77968e","first_computed_at":"2026-07-05T10:09:40.672253Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:40.672253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/flHTHcnXYhQ7t12uPWJGz+jAhuDFd1LsK4Xoubp0txNSeGnazEVTt9hl6RZvFv8bUpt0d4lUxumjQar66cKAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:40.672663Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.13994","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6c4f501c187045e925b82c9f89dc63ec897308f15d7acdd2635ffc4246ce8fe","sha256:bbde2a3c5659fc7a794e13403469aaa49383b730b3ceed080de8b15ac24e9f98"],"state_sha256":"2369a5b935be534f396ca6d5ab919735605f1251269bbd84a08ae9874cf641a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ImTyeEwZHr/ZXfd1m1gtDB3fdnHWJDtDBO7YdJKp3V1WyMzkc4nVOsUIvo5rQ7i+24AlDmrGofLYVw6hbOSnCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T06:58:28.925649Z","bundle_sha256":"bb90109e32c4a39b74cad6bd191c4058bd00c12260651d6969aa397bdab38704"}}