{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:P46UJROGEIJDOSIX47KGCL7RLL","short_pith_number":"pith:P46UJROG","schema_version":"1.0","canonical_sha256":"7f3d44c5c62212374917e7d4612ff15aea70e1875b2237cbd9aa3d3b6b26a5bf","source":{"kind":"arxiv","id":"2010.14791","version":3},"attestation_state":"computed","paper":{"title":"One In A Hundred: Select The Best Predicted Sequence from Numerous Candidates for Streaming Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Jiangyan Yi, Jianhua Tao, Shuai Zhang, Ye Bai, Zhengkun Tian, Zhengqi Wen","submitted_at":"2020-10-28T07:07:01Z","abstract_excerpt":"The RNN-Transducers and improved attention-based encoder-decoder models are widely applied to streaming speech recognition. Compared with these two end-to-end models, the CTC model is more efficient in training and inference. However, it cannot capture the linguistic dependencies between the output tokens. Inspired by the success of two-pass end-to-end models, we introduce a transformer decoder and the two-stage inference method into the streaming CTC model. During inference, the CTC decoder first generates many candidates in a streaming fashion. Then the transformer decoder selects the best c"},"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":"2010.14791","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-10-28T07:07:01Z","cross_cats_sorted":[],"title_canon_sha256":"6d3c8240ec5b4e9398001c4f9d243fded7ed2262778191b92d7e4e7ec6be1bd3","abstract_canon_sha256":"9e26988bca2c9ef16ec8c16a8aa65cd25fd8ac1ae641c6faf28bbaa19835c2f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:28:52.881954Z","signature_b64":"2CJB4TOYyb8J6gQ6go25RHneBjdjf8AmQV0G49ZONp9JKyG822I44HspOnVXfPEDeJjQKcOV/fxgqQ7LRC+mCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f3d44c5c62212374917e7d4612ff15aea70e1875b2237cbd9aa3d3b6b26a5bf","last_reissued_at":"2026-07-05T02:28:52.881487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:28:52.881487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One In A Hundred: Select The Best Predicted Sequence from Numerous Candidates for Streaming Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Jiangyan Yi, Jianhua Tao, Shuai Zhang, Ye Bai, Zhengkun Tian, Zhengqi Wen","submitted_at":"2020-10-28T07:07:01Z","abstract_excerpt":"The RNN-Transducers and improved attention-based encoder-decoder models are widely applied to streaming speech recognition. Compared with these two end-to-end models, the CTC model is more efficient in training and inference. However, it cannot capture the linguistic dependencies between the output tokens. Inspired by the success of two-pass end-to-end models, we introduce a transformer decoder and the two-stage inference method into the streaming CTC model. During inference, the CTC decoder first generates many candidates in a streaming fashion. Then the transformer decoder selects the best c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.14791","kind":"arxiv","version":3},"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/2010.14791/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":"2010.14791","created_at":"2026-07-05T02:28:52.881548+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.14791v3","created_at":"2026-07-05T02:28:52.881548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.14791","created_at":"2026-07-05T02:28:52.881548+00:00"},{"alias_kind":"pith_short_12","alias_value":"P46UJROGEIJD","created_at":"2026-07-05T02:28:52.881548+00:00"},{"alias_kind":"pith_short_16","alias_value":"P46UJROGEIJDOSIX","created_at":"2026-07-05T02:28:52.881548+00:00"},{"alias_kind":"pith_short_8","alias_value":"P46UJROG","created_at":"2026-07-05T02:28:52.881548+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/P46UJROGEIJDOSIX47KGCL7RLL","json":"https://pith.science/pith/P46UJROGEIJDOSIX47KGCL7RLL.json","graph_json":"https://pith.science/api/pith-number/P46UJROGEIJDOSIX47KGCL7RLL/graph.json","events_json":"https://pith.science/api/pith-number/P46UJROGEIJDOSIX47KGCL7RLL/events.json","paper":"https://pith.science/paper/P46UJROG"},"agent_actions":{"view_html":"https://pith.science/pith/P46UJROGEIJDOSIX47KGCL7RLL","download_json":"https://pith.science/pith/P46UJROGEIJDOSIX47KGCL7RLL.json","view_paper":"https://pith.science/paper/P46UJROG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.14791&json=true","fetch_graph":"https://pith.science/api/pith-number/P46UJROGEIJDOSIX47KGCL7RLL/graph.json","fetch_events":"https://pith.science/api/pith-number/P46UJROGEIJDOSIX47KGCL7RLL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P46UJROGEIJDOSIX47KGCL7RLL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P46UJROGEIJDOSIX47KGCL7RLL/action/storage_attestation","attest_author":"https://pith.science/pith/P46UJROGEIJDOSIX47KGCL7RLL/action/author_attestation","sign_citation":"https://pith.science/pith/P46UJROGEIJDOSIX47KGCL7RLL/action/citation_signature","submit_replication":"https://pith.science/pith/P46UJROGEIJDOSIX47KGCL7RLL/action/replication_record"}},"created_at":"2026-07-05T02:28:52.881548+00:00","updated_at":"2026-07-05T02:28:52.881548+00:00"}