{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WBKOWKJ6PDLLVAMHQIHU5F5DIJ","short_pith_number":"pith:WBKOWKJ6","schema_version":"1.0","canonical_sha256":"b054eb293e78d6ba8187820f4e97a3425d103183f499535a854432d6b8604105","source":{"kind":"arxiv","id":"2312.09582","version":1},"attestation_state":"computed","paper":{"title":"Phoneme-aware Encoding for Prefix-tree-based Contextual ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Emiru Tsunoo, Hayato Futami, Hiroaki Ogawa, Shinji Watanabe, Siddhant Arora, Yosuke Kashiwagi","submitted_at":"2023-12-15T07:37:09Z","abstract_excerpt":"In speech recognition applications, it is important to recognize context-specific rare words, such as proper nouns. Tree-constrained Pointer Generator (TCPGen) has shown promise for this purpose, which efficiently biases such words with a prefix tree. While the original TCPGen relies on grapheme-based encoding, we propose extending it with phoneme-aware encoding to better recognize words of unusual pronunciations. As TCPGen handles biasing words as subword units, we propose obtaining subword-level phoneme-aware encoding by using alignment between phonemes and subwords. Furthermore, we propose "},"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":"2312.09582","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-15T07:37:09Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"ee73b56959cee70909dd76a1851f94eb55df468bd3585f19f4997c2823b7aeb1","abstract_canon_sha256":"185cee4c17802f9cd4ff7b676e62a006d7cf72ff820fcd7c5e81af289c365429"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:27.635754Z","signature_b64":"xiRx/7E+bOiTMeEJu4YZEmE1wyYAgVO/kt1MNvD38DsGLTmUU0/rEajFtMJIIJeSjA9aqfqfSsxS4d+mnvDfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b054eb293e78d6ba8187820f4e97a3425d103183f499535a854432d6b8604105","last_reissued_at":"2026-07-05T07:24:27.635151Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:27.635151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Phoneme-aware Encoding for Prefix-tree-based Contextual ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Emiru Tsunoo, Hayato Futami, Hiroaki Ogawa, Shinji Watanabe, Siddhant Arora, Yosuke Kashiwagi","submitted_at":"2023-12-15T07:37:09Z","abstract_excerpt":"In speech recognition applications, it is important to recognize context-specific rare words, such as proper nouns. Tree-constrained Pointer Generator (TCPGen) has shown promise for this purpose, which efficiently biases such words with a prefix tree. While the original TCPGen relies on grapheme-based encoding, we propose extending it with phoneme-aware encoding to better recognize words of unusual pronunciations. As TCPGen handles biasing words as subword units, we propose obtaining subword-level phoneme-aware encoding by using alignment between phonemes and subwords. Furthermore, we propose "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09582","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/2312.09582/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":"2312.09582","created_at":"2026-07-05T07:24:27.635214+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.09582v1","created_at":"2026-07-05T07:24:27.635214+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09582","created_at":"2026-07-05T07:24:27.635214+00:00"},{"alias_kind":"pith_short_12","alias_value":"WBKOWKJ6PDLL","created_at":"2026-07-05T07:24:27.635214+00:00"},{"alias_kind":"pith_short_16","alias_value":"WBKOWKJ6PDLLVAMH","created_at":"2026-07-05T07:24:27.635214+00:00"},{"alias_kind":"pith_short_8","alias_value":"WBKOWKJ6","created_at":"2026-07-05T07:24:27.635214+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/WBKOWKJ6PDLLVAMHQIHU5F5DIJ","json":"https://pith.science/pith/WBKOWKJ6PDLLVAMHQIHU5F5DIJ.json","graph_json":"https://pith.science/api/pith-number/WBKOWKJ6PDLLVAMHQIHU5F5DIJ/graph.json","events_json":"https://pith.science/api/pith-number/WBKOWKJ6PDLLVAMHQIHU5F5DIJ/events.json","paper":"https://pith.science/paper/WBKOWKJ6"},"agent_actions":{"view_html":"https://pith.science/pith/WBKOWKJ6PDLLVAMHQIHU5F5DIJ","download_json":"https://pith.science/pith/WBKOWKJ6PDLLVAMHQIHU5F5DIJ.json","view_paper":"https://pith.science/paper/WBKOWKJ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.09582&json=true","fetch_graph":"https://pith.science/api/pith-number/WBKOWKJ6PDLLVAMHQIHU5F5DIJ/graph.json","fetch_events":"https://pith.science/api/pith-number/WBKOWKJ6PDLLVAMHQIHU5F5DIJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WBKOWKJ6PDLLVAMHQIHU5F5DIJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WBKOWKJ6PDLLVAMHQIHU5F5DIJ/action/storage_attestation","attest_author":"https://pith.science/pith/WBKOWKJ6PDLLVAMHQIHU5F5DIJ/action/author_attestation","sign_citation":"https://pith.science/pith/WBKOWKJ6PDLLVAMHQIHU5F5DIJ/action/citation_signature","submit_replication":"https://pith.science/pith/WBKOWKJ6PDLLVAMHQIHU5F5DIJ/action/replication_record"}},"created_at":"2026-07-05T07:24:27.635214+00:00","updated_at":"2026-07-05T07:24:27.635214+00:00"}