{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2G7BWJ55WOADVCITTGJGIXT7HB","short_pith_number":"pith:2G7BWJ55","schema_version":"1.0","canonical_sha256":"d1be1b27bdb3803a89139992645e7f38698dac0088c72ed691aa977e9ebb007f","source":{"kind":"arxiv","id":"1805.06239","version":2},"attestation_state":"computed","paper":{"title":"A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Bo Xu, Linhao Dong, Shiyu Zhou, Shuang Xu","submitted_at":"2018-05-16T10:43:47Z","abstract_excerpt":"The choice of modeling units is critical to automatic speech recognition (ASR) tasks. Conventional ASR systems typically choose context-dependent states (CD-states) or context-dependent phonemes (CD-phonemes) as their modeling units. However, it has been challenged by sequence-to-sequence attention-based models, which integrate an acoustic, pronunciation and language model into a single neural network. On English ASR tasks, previous attempts have already shown that the modeling unit of graphemes can outperform that of phonemes by sequence-to-sequence attention-based model.\n  In this paper, we "},"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":"1805.06239","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-05-16T10:43:47Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"6b37fe5936bd2ac1fa65f1831e557953100936dccdcee08fd1d7d15d00c23c46","abstract_canon_sha256":"835e5e3c864a734fc52a91099ef94c046f52daba6bf59bbb449af4d18f6c3406"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:36.088273Z","signature_b64":"uYTiaHqeEA4XeWGqsoEYRQ5pB9EyLgmoBSCe9ERmn985XaFQQp53Kq8kqH1P4Yx3ASlF2WTcZd6SKCfcFt75AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1be1b27bdb3803a89139992645e7f38698dac0088c72ed691aa977e9ebb007f","last_reissued_at":"2026-05-18T00:15:36.087439Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:36.087439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Bo Xu, Linhao Dong, Shiyu Zhou, Shuang Xu","submitted_at":"2018-05-16T10:43:47Z","abstract_excerpt":"The choice of modeling units is critical to automatic speech recognition (ASR) tasks. Conventional ASR systems typically choose context-dependent states (CD-states) or context-dependent phonemes (CD-phonemes) as their modeling units. However, it has been challenged by sequence-to-sequence attention-based models, which integrate an acoustic, pronunciation and language model into a single neural network. On English ASR tasks, previous attempts have already shown that the modeling unit of graphemes can outperform that of phonemes by sequence-to-sequence attention-based model.\n  In this paper, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.06239","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":""},"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":"1805.06239","created_at":"2026-05-18T00:15:36.087553+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.06239v2","created_at":"2026-05-18T00:15:36.087553+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.06239","created_at":"2026-05-18T00:15:36.087553+00:00"},{"alias_kind":"pith_short_12","alias_value":"2G7BWJ55WOAD","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"2G7BWJ55WOADVCIT","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"2G7BWJ55","created_at":"2026-05-18T12:32:02.567920+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/2G7BWJ55WOADVCITTGJGIXT7HB","json":"https://pith.science/pith/2G7BWJ55WOADVCITTGJGIXT7HB.json","graph_json":"https://pith.science/api/pith-number/2G7BWJ55WOADVCITTGJGIXT7HB/graph.json","events_json":"https://pith.science/api/pith-number/2G7BWJ55WOADVCITTGJGIXT7HB/events.json","paper":"https://pith.science/paper/2G7BWJ55"},"agent_actions":{"view_html":"https://pith.science/pith/2G7BWJ55WOADVCITTGJGIXT7HB","download_json":"https://pith.science/pith/2G7BWJ55WOADVCITTGJGIXT7HB.json","view_paper":"https://pith.science/paper/2G7BWJ55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.06239&json=true","fetch_graph":"https://pith.science/api/pith-number/2G7BWJ55WOADVCITTGJGIXT7HB/graph.json","fetch_events":"https://pith.science/api/pith-number/2G7BWJ55WOADVCITTGJGIXT7HB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2G7BWJ55WOADVCITTGJGIXT7HB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2G7BWJ55WOADVCITTGJGIXT7HB/action/storage_attestation","attest_author":"https://pith.science/pith/2G7BWJ55WOADVCITTGJGIXT7HB/action/author_attestation","sign_citation":"https://pith.science/pith/2G7BWJ55WOADVCITTGJGIXT7HB/action/citation_signature","submit_replication":"https://pith.science/pith/2G7BWJ55WOADVCITTGJGIXT7HB/action/replication_record"}},"created_at":"2026-05-18T00:15:36.087553+00:00","updated_at":"2026-05-18T00:15:36.087553+00:00"}