{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RZAJAYWYEUYV5XXTY6ZK5RHNJE","short_pith_number":"pith:RZAJAYWY","schema_version":"1.0","canonical_sha256":"8e409062d825315edef3c7b2aec4ed492fd160bb0296c9fc35c84deeefec72aa","source":{"kind":"arxiv","id":"1804.10752","version":2},"attestation_state":"computed","paper":{"title":"Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in 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":"2018-04-28T06:54:11Z","abstract_excerpt":"Sequence-to-sequence attention-based models have recently shown very promising results on automatic speech recognition (ASR) tasks, which integrate an acoustic, pronunciation and language model into a single neural network. In these models, the Transformer, a new sequence-to-sequence attention-based model relying entirely on self-attention without using RNNs or convolutions, achieves a new single-model state-of-the-art BLEU on neural machine translation (NMT) tasks. Since the outstanding performance of the Transformer, we extend it to speech and concentrate on it as the basic architecture of s"},"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":"1804.10752","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-04-28T06:54:11Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"c2004ccbafcaa0efc2161c7a753287eebc7f9bc71237e3d7cad7eafd864e826b","abstract_canon_sha256":"b76e5be19ac9d1d765b478e8b894550456d89a8ee96423225af60c8343f9015a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:21.380648Z","signature_b64":"CyO8OXsISG/dxkRLHe2DaMeHUTbonxJnR/GM0EmPjKVc8OU0BxohfNf4FpnrOM9Lws4p8mDW2padXoYXAuF5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e409062d825315edef3c7b2aec4ed492fd160bb0296c9fc35c84deeefec72aa","last_reissued_at":"2026-05-18T00:14:21.380066Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:21.380066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in 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":"2018-04-28T06:54:11Z","abstract_excerpt":"Sequence-to-sequence attention-based models have recently shown very promising results on automatic speech recognition (ASR) tasks, which integrate an acoustic, pronunciation and language model into a single neural network. In these models, the Transformer, a new sequence-to-sequence attention-based model relying entirely on self-attention without using RNNs or convolutions, achieves a new single-model state-of-the-art BLEU on neural machine translation (NMT) tasks. Since the outstanding performance of the Transformer, we extend it to speech and concentrate on it as the basic architecture of s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.10752","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":"1804.10752","created_at":"2026-05-18T00:14:21.380134+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.10752v2","created_at":"2026-05-18T00:14:21.380134+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.10752","created_at":"2026-05-18T00:14:21.380134+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZAJAYWYEUYV","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZAJAYWYEUYV5XXT","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZAJAYWY","created_at":"2026-05-18T12:32:50.500415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1907.03233","citing_title":"NIESR: Nuisance Invariant End-to-end Speech Recognition","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06017","citing_title":"Learn Spelling from Teachers: Transferring Knowledge from Language Models to Sequence-to-Sequence Speech Recognition","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"1910.07467","citing_title":"Root Mean Square Layer Normalization","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RZAJAYWYEUYV5XXTY6ZK5RHNJE","json":"https://pith.science/pith/RZAJAYWYEUYV5XXTY6ZK5RHNJE.json","graph_json":"https://pith.science/api/pith-number/RZAJAYWYEUYV5XXTY6ZK5RHNJE/graph.json","events_json":"https://pith.science/api/pith-number/RZAJAYWYEUYV5XXTY6ZK5RHNJE/events.json","paper":"https://pith.science/paper/RZAJAYWY"},"agent_actions":{"view_html":"https://pith.science/pith/RZAJAYWYEUYV5XXTY6ZK5RHNJE","download_json":"https://pith.science/pith/RZAJAYWYEUYV5XXTY6ZK5RHNJE.json","view_paper":"https://pith.science/paper/RZAJAYWY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.10752&json=true","fetch_graph":"https://pith.science/api/pith-number/RZAJAYWYEUYV5XXTY6ZK5RHNJE/graph.json","fetch_events":"https://pith.science/api/pith-number/RZAJAYWYEUYV5XXTY6ZK5RHNJE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZAJAYWYEUYV5XXTY6ZK5RHNJE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZAJAYWYEUYV5XXTY6ZK5RHNJE/action/storage_attestation","attest_author":"https://pith.science/pith/RZAJAYWYEUYV5XXTY6ZK5RHNJE/action/author_attestation","sign_citation":"https://pith.science/pith/RZAJAYWYEUYV5XXTY6ZK5RHNJE/action/citation_signature","submit_replication":"https://pith.science/pith/RZAJAYWYEUYV5XXTY6ZK5RHNJE/action/replication_record"}},"created_at":"2026-05-18T00:14:21.380134+00:00","updated_at":"2026-05-18T00:14:21.380134+00:00"}