{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NDZSRUR7FPP7A3XFCJC63444KG","short_pith_number":"pith:NDZSRUR7","schema_version":"1.0","canonical_sha256":"68f328d23f2bdff06ee51245edf39c519fa6215739f44768b7f56a7915336e1b","source":{"kind":"arxiv","id":"1811.04897","version":1},"attestation_state":"computed","paper":{"title":"Multi-encoder multi-resolution framework for end-to-end speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hynek Hermansky, Ruizhi Li, Shinji Watanabe, Sri Harish Mallidi, Takaaki Hori, Xiaofei Wang","submitted_at":"2018-11-12T18:33:21Z","abstract_excerpt":"Attention-based methods and Connectionist Temporal Classification (CTC) network have been promising research directions for end-to-end Automatic Speech Recognition (ASR). The joint CTC/Attention model has achieved great success by utilizing both architectures during multi-task training and joint decoding. In this work, we present a novel Multi-Encoder Multi-Resolution (MEMR) framework based on the joint CTC/Attention model. Two heterogeneous encoders with different architectures, temporal resolutions and separate CTC networks work in parallel to extract complimentary acoustic information. A hi"},"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":"1811.04897","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-12T18:33:21Z","cross_cats_sorted":[],"title_canon_sha256":"5281d193073db0e000712fc8d14998bea06d695fdc24465fcb9ec6d7d7bd56ff","abstract_canon_sha256":"de927b18873ed0ccf6e9f2cb7a77164fdcb6483a1a6e34c34ccf209e551536c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:02.138964Z","signature_b64":"Oh2upGCWSBC7jpoQB8270F+SA+t9qBE82WS/WTpdODGjYvzwcX3ez7Tz/lufCpUilUxmYaBkyQqO59UKCrOIBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68f328d23f2bdff06ee51245edf39c519fa6215739f44768b7f56a7915336e1b","last_reissued_at":"2026-05-18T00:01:02.138368Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:02.138368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-encoder multi-resolution framework for end-to-end speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hynek Hermansky, Ruizhi Li, Shinji Watanabe, Sri Harish Mallidi, Takaaki Hori, Xiaofei Wang","submitted_at":"2018-11-12T18:33:21Z","abstract_excerpt":"Attention-based methods and Connectionist Temporal Classification (CTC) network have been promising research directions for end-to-end Automatic Speech Recognition (ASR). The joint CTC/Attention model has achieved great success by utilizing both architectures during multi-task training and joint decoding. In this work, we present a novel Multi-Encoder Multi-Resolution (MEMR) framework based on the joint CTC/Attention model. Two heterogeneous encoders with different architectures, temporal resolutions and separate CTC networks work in parallel to extract complimentary acoustic information. A hi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.04897","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":"1811.04897","created_at":"2026-05-18T00:01:02.138474+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.04897v1","created_at":"2026-05-18T00:01:02.138474+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.04897","created_at":"2026-05-18T00:01:02.138474+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDZSRUR7FPP7","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDZSRUR7FPP7A3XF","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDZSRUR7","created_at":"2026-05-18T12:32:40.477152+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/NDZSRUR7FPP7A3XFCJC63444KG","json":"https://pith.science/pith/NDZSRUR7FPP7A3XFCJC63444KG.json","graph_json":"https://pith.science/api/pith-number/NDZSRUR7FPP7A3XFCJC63444KG/graph.json","events_json":"https://pith.science/api/pith-number/NDZSRUR7FPP7A3XFCJC63444KG/events.json","paper":"https://pith.science/paper/NDZSRUR7"},"agent_actions":{"view_html":"https://pith.science/pith/NDZSRUR7FPP7A3XFCJC63444KG","download_json":"https://pith.science/pith/NDZSRUR7FPP7A3XFCJC63444KG.json","view_paper":"https://pith.science/paper/NDZSRUR7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.04897&json=true","fetch_graph":"https://pith.science/api/pith-number/NDZSRUR7FPP7A3XFCJC63444KG/graph.json","fetch_events":"https://pith.science/api/pith-number/NDZSRUR7FPP7A3XFCJC63444KG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDZSRUR7FPP7A3XFCJC63444KG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDZSRUR7FPP7A3XFCJC63444KG/action/storage_attestation","attest_author":"https://pith.science/pith/NDZSRUR7FPP7A3XFCJC63444KG/action/author_attestation","sign_citation":"https://pith.science/pith/NDZSRUR7FPP7A3XFCJC63444KG/action/citation_signature","submit_replication":"https://pith.science/pith/NDZSRUR7FPP7A3XFCJC63444KG/action/replication_record"}},"created_at":"2026-05-18T00:01:02.138474+00:00","updated_at":"2026-05-18T00:01:02.138474+00:00"}