{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:Q3ELL3MAVLDYDC36OT343UOVMY","short_pith_number":"pith:Q3ELL3MA","schema_version":"1.0","canonical_sha256":"86c8b5ed80aac7818b7e74f7cdd1d5661f53b09faa29c60613db2db1cc461467","source":{"kind":"arxiv","id":"2001.08290","version":2},"attestation_state":"computed","paper":{"title":"Transformer-based Online CTC/attention End-to-End Speech Recognition Architecture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Changfeng Gao, Gaofeng Cheng, Haoran Miao, Pengyuan Zhang, Yonghong Yan","submitted_at":"2020-01-15T14:36:19Z","abstract_excerpt":"Recently, Transformer has gained success in automatic speech recognition (ASR) field. However, it is challenging to deploy a Transformer-based end-to-end (E2E) model for online speech recognition. In this paper, we propose the Transformer-based online CTC/attention E2E ASR architecture, which contains the chunk self-attention encoder (chunk-SAE) and the monotonic truncated attention (MTA) based self-attention decoder (SAD). Firstly, the chunk-SAE splits the speech into isolated chunks. To reduce the computational cost and improve the performance, we propose the state reuse chunk-SAE. Sencondly"},"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":"2001.08290","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-01-15T14:36:19Z","cross_cats_sorted":["cs.LG","cs.NE","cs.SD","stat.ML"],"title_canon_sha256":"c793ea9c63b2686c0a2a991db362cd647e6e26a3984e66eaf3cb93acc351cee1","abstract_canon_sha256":"834c4798e6c5e2bfef42fc63d8d895112b22389709335a382705af4d2e591fc7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:39:41.037708Z","signature_b64":"+xUII4aioXZSN295lVSrvQsJY7SNjYmT/yXfKNdISPq7dKwENteNaYAHeFXIWyf5GYGfuZoK3PsTqtrI5JR1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86c8b5ed80aac7818b7e74f7cdd1d5661f53b09faa29c60613db2db1cc461467","last_reissued_at":"2026-07-05T00:39:41.037360Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:39:41.037360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformer-based Online CTC/attention End-to-End Speech Recognition Architecture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Changfeng Gao, Gaofeng Cheng, Haoran Miao, Pengyuan Zhang, Yonghong Yan","submitted_at":"2020-01-15T14:36:19Z","abstract_excerpt":"Recently, Transformer has gained success in automatic speech recognition (ASR) field. However, it is challenging to deploy a Transformer-based end-to-end (E2E) model for online speech recognition. In this paper, we propose the Transformer-based online CTC/attention E2E ASR architecture, which contains the chunk self-attention encoder (chunk-SAE) and the monotonic truncated attention (MTA) based self-attention decoder (SAD). Firstly, the chunk-SAE splits the speech into isolated chunks. To reduce the computational cost and improve the performance, we propose the state reuse chunk-SAE. Sencondly"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.08290","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2001.08290/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":"2001.08290","created_at":"2026-07-05T00:39:41.037423+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.08290v2","created_at":"2026-07-05T00:39:41.037423+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.08290","created_at":"2026-07-05T00:39:41.037423+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3ELL3MAVLDY","created_at":"2026-07-05T00:39:41.037423+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3ELL3MAVLDYDC36","created_at":"2026-07-05T00:39:41.037423+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3ELL3MA","created_at":"2026-07-05T00:39:41.037423+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/Q3ELL3MAVLDYDC36OT343UOVMY","json":"https://pith.science/pith/Q3ELL3MAVLDYDC36OT343UOVMY.json","graph_json":"https://pith.science/api/pith-number/Q3ELL3MAVLDYDC36OT343UOVMY/graph.json","events_json":"https://pith.science/api/pith-number/Q3ELL3MAVLDYDC36OT343UOVMY/events.json","paper":"https://pith.science/paper/Q3ELL3MA"},"agent_actions":{"view_html":"https://pith.science/pith/Q3ELL3MAVLDYDC36OT343UOVMY","download_json":"https://pith.science/pith/Q3ELL3MAVLDYDC36OT343UOVMY.json","view_paper":"https://pith.science/paper/Q3ELL3MA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.08290&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3ELL3MAVLDYDC36OT343UOVMY/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3ELL3MAVLDYDC36OT343UOVMY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3ELL3MAVLDYDC36OT343UOVMY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3ELL3MAVLDYDC36OT343UOVMY/action/storage_attestation","attest_author":"https://pith.science/pith/Q3ELL3MAVLDYDC36OT343UOVMY/action/author_attestation","sign_citation":"https://pith.science/pith/Q3ELL3MAVLDYDC36OT343UOVMY/action/citation_signature","submit_replication":"https://pith.science/pith/Q3ELL3MAVLDYDC36OT343UOVMY/action/replication_record"}},"created_at":"2026-07-05T00:39:41.037423+00:00","updated_at":"2026-07-05T00:39:41.037423+00:00"}