{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:IOCIHBAMY6HYDPIYIXH3TIBR7E","short_pith_number":"pith:IOCIHBAM","schema_version":"1.0","canonical_sha256":"438483840cc78f81bd1845cfb9a031f92fda6171815528fa9ac4d95003b4859d","source":{"kind":"arxiv","id":"1712.01864","version":1},"attestation_state":"computed","paper":{"title":"No Need for a Lexicon? Evaluating the Value of the Pronunciation Lexica in End-to-End Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS","stat.ML"],"primary_cat":"cs.CL","authors_text":"Anjuli Kannan, Bo Li, Chung-Cheng Chiu, David Rybach, Patrick Nguyen, Rohit Prabhavalkar, Seungji Lee, Shankar Kumar, Tara N. Sainath, Vlad Schogol, Yonghui Wu, Zhifeng Chen","submitted_at":"2017-12-05T19:02:28Z","abstract_excerpt":"For decades, context-dependent phonemes have been the dominant sub-word unit for conventional acoustic modeling systems. This status quo has begun to be challenged recently by end-to-end models which seek to combine acoustic, pronunciation, and language model components into a single neural network. Such systems, which typically predict graphemes or words, simplify the recognition process since they remove the need for a separate expert-curated pronunciation lexicon to map from phoneme-based units to words. However, there has been little previous work comparing phoneme-based versus grapheme-ba"},"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":"1712.01864","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-12-05T19:02:28Z","cross_cats_sorted":["cs.SD","eess.AS","stat.ML"],"title_canon_sha256":"89f1c44ca34e7b96cd0e56cb702263ebbda5c779667a1e3e0afeb148f45465ee","abstract_canon_sha256":"dfee4931b3ca40e30bcdefb430f887debe6e8c1a8b7740c5110006716f588962"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:39.878733Z","signature_b64":"4FB7ev3YOBsrvMdUWZyVki9qqWuoUqGYAjqIqW0OBhGThxLsW2AOrwuM9g6VVhMpVWBUCejEyfoL6wu28AGYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"438483840cc78f81bd1845cfb9a031f92fda6171815528fa9ac4d95003b4859d","last_reissued_at":"2026-05-18T00:28:39.877954Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:39.877954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"No Need for a Lexicon? Evaluating the Value of the Pronunciation Lexica in End-to-End Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS","stat.ML"],"primary_cat":"cs.CL","authors_text":"Anjuli Kannan, Bo Li, Chung-Cheng Chiu, David Rybach, Patrick Nguyen, Rohit Prabhavalkar, Seungji Lee, Shankar Kumar, Tara N. Sainath, Vlad Schogol, Yonghui Wu, Zhifeng Chen","submitted_at":"2017-12-05T19:02:28Z","abstract_excerpt":"For decades, context-dependent phonemes have been the dominant sub-word unit for conventional acoustic modeling systems. This status quo has begun to be challenged recently by end-to-end models which seek to combine acoustic, pronunciation, and language model components into a single neural network. Such systems, which typically predict graphemes or words, simplify the recognition process since they remove the need for a separate expert-curated pronunciation lexicon to map from phoneme-based units to words. However, there has been little previous work comparing phoneme-based versus grapheme-ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.01864","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":""},"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":"1712.01864","created_at":"2026-05-18T00:28:39.878055+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.01864v1","created_at":"2026-05-18T00:28:39.878055+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.01864","created_at":"2026-05-18T00:28:39.878055+00:00"},{"alias_kind":"pith_short_12","alias_value":"IOCIHBAMY6HY","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"IOCIHBAMY6HYDPIY","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"IOCIHBAM","created_at":"2026-05-18T12:31:21.493067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.08293","citing_title":"Investigating Target Set Reduction for End-to-End Speech Recognition of Hindi-English Code-Switching Data","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IOCIHBAMY6HYDPIYIXH3TIBR7E","json":"https://pith.science/pith/IOCIHBAMY6HYDPIYIXH3TIBR7E.json","graph_json":"https://pith.science/api/pith-number/IOCIHBAMY6HYDPIYIXH3TIBR7E/graph.json","events_json":"https://pith.science/api/pith-number/IOCIHBAMY6HYDPIYIXH3TIBR7E/events.json","paper":"https://pith.science/paper/IOCIHBAM"},"agent_actions":{"view_html":"https://pith.science/pith/IOCIHBAMY6HYDPIYIXH3TIBR7E","download_json":"https://pith.science/pith/IOCIHBAMY6HYDPIYIXH3TIBR7E.json","view_paper":"https://pith.science/paper/IOCIHBAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.01864&json=true","fetch_graph":"https://pith.science/api/pith-number/IOCIHBAMY6HYDPIYIXH3TIBR7E/graph.json","fetch_events":"https://pith.science/api/pith-number/IOCIHBAMY6HYDPIYIXH3TIBR7E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IOCIHBAMY6HYDPIYIXH3TIBR7E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IOCIHBAMY6HYDPIYIXH3TIBR7E/action/storage_attestation","attest_author":"https://pith.science/pith/IOCIHBAMY6HYDPIYIXH3TIBR7E/action/author_attestation","sign_citation":"https://pith.science/pith/IOCIHBAMY6HYDPIYIXH3TIBR7E/action/citation_signature","submit_replication":"https://pith.science/pith/IOCIHBAMY6HYDPIYIXH3TIBR7E/action/replication_record"}},"created_at":"2026-05-18T00:28:39.878055+00:00","updated_at":"2026-05-18T00:28:39.878055+00:00"}