{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TKB66VXGT4H7FE3BGDUK36OJLZ","short_pith_number":"pith:TKB66VXG","schema_version":"1.0","canonical_sha256":"9a83ef56e69f0ff2936130e8adf9c95e6fc355d81a847382280506d0cba3e8f5","source":{"kind":"arxiv","id":"2310.09988","version":1},"attestation_state":"computed","paper":{"title":"Personalization of CTC-based End-to-End Speech Recognition Using Pronunciation-Driven Subword Tokenization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ernest Pusateri, Leo Liu, Man-Hung Siu, Mingbin Xu, Mirko Hannemann, Ruchir Travadi, Shiyi Han, Tim Ng, Youyuan Zhang, Zhen Huang, Zhihong Lei","submitted_at":"2023-10-16T00:06:32Z","abstract_excerpt":"Recent advances in deep learning and automatic speech recognition have improved the accuracy of end-to-end speech recognition systems, but recognition of personal content such as contact names remains a challenge. In this work, we describe our personalization solution for an end-to-end speech recognition system based on connectionist temporal classification. Building on previous work, we present a novel method for generating additional subword tokenizations for personal entities from their pronunciations. We show that using this technique in combination with two established techniques, context"},"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":"2310.09988","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T00:06:32Z","cross_cats_sorted":[],"title_canon_sha256":"2f5ef69cda06d9ab56e770b22df3e7cf0b44677e53c36d1e4d5ee99e57d6ff18","abstract_canon_sha256":"80b2b9701f2fc41fa068d2050ca4961a8084b631ad2501137d33e224251f6037"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:13.432580Z","signature_b64":"VgvJbRZTqKUsBJPhwRgH/lHYat3f/PGSc4LzVuc2539J36otJw5NmL5JjRJ7RLf+87xFk+duDPlbo3gB21kaAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a83ef56e69f0ff2936130e8adf9c95e6fc355d81a847382280506d0cba3e8f5","last_reissued_at":"2026-07-05T07:01:13.432170Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:13.432170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Personalization of CTC-based End-to-End Speech Recognition Using Pronunciation-Driven Subword Tokenization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ernest Pusateri, Leo Liu, Man-Hung Siu, Mingbin Xu, Mirko Hannemann, Ruchir Travadi, Shiyi Han, Tim Ng, Youyuan Zhang, Zhen Huang, Zhihong Lei","submitted_at":"2023-10-16T00:06:32Z","abstract_excerpt":"Recent advances in deep learning and automatic speech recognition have improved the accuracy of end-to-end speech recognition systems, but recognition of personal content such as contact names remains a challenge. In this work, we describe our personalization solution for an end-to-end speech recognition system based on connectionist temporal classification. Building on previous work, we present a novel method for generating additional subword tokenizations for personal entities from their pronunciations. We show that using this technique in combination with two established techniques, context"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09988","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/2310.09988/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":"2310.09988","created_at":"2026-07-05T07:01:13.432227+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.09988v1","created_at":"2026-07-05T07:01:13.432227+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09988","created_at":"2026-07-05T07:01:13.432227+00:00"},{"alias_kind":"pith_short_12","alias_value":"TKB66VXGT4H7","created_at":"2026-07-05T07:01:13.432227+00:00"},{"alias_kind":"pith_short_16","alias_value":"TKB66VXGT4H7FE3B","created_at":"2026-07-05T07:01:13.432227+00:00"},{"alias_kind":"pith_short_8","alias_value":"TKB66VXG","created_at":"2026-07-05T07:01:13.432227+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TKB66VXGT4H7FE3BGDUK36OJLZ","json":"https://pith.science/pith/TKB66VXGT4H7FE3BGDUK36OJLZ.json","graph_json":"https://pith.science/api/pith-number/TKB66VXGT4H7FE3BGDUK36OJLZ/graph.json","events_json":"https://pith.science/api/pith-number/TKB66VXGT4H7FE3BGDUK36OJLZ/events.json","paper":"https://pith.science/paper/TKB66VXG"},"agent_actions":{"view_html":"https://pith.science/pith/TKB66VXGT4H7FE3BGDUK36OJLZ","download_json":"https://pith.science/pith/TKB66VXGT4H7FE3BGDUK36OJLZ.json","view_paper":"https://pith.science/paper/TKB66VXG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.09988&json=true","fetch_graph":"https://pith.science/api/pith-number/TKB66VXGT4H7FE3BGDUK36OJLZ/graph.json","fetch_events":"https://pith.science/api/pith-number/TKB66VXGT4H7FE3BGDUK36OJLZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TKB66VXGT4H7FE3BGDUK36OJLZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TKB66VXGT4H7FE3BGDUK36OJLZ/action/storage_attestation","attest_author":"https://pith.science/pith/TKB66VXGT4H7FE3BGDUK36OJLZ/action/author_attestation","sign_citation":"https://pith.science/pith/TKB66VXGT4H7FE3BGDUK36OJLZ/action/citation_signature","submit_replication":"https://pith.science/pith/TKB66VXGT4H7FE3BGDUK36OJLZ/action/replication_record"}},"created_at":"2026-07-05T07:01:13.432227+00:00","updated_at":"2026-07-05T07:01:13.432227+00:00"}