{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H2BTFYMNN2A5JF2J45VXRQZVRX","short_pith_number":"pith:H2BTFYMN","schema_version":"1.0","canonical_sha256":"3e8332e18d6e81d49749e76b78c3358df5d8c26c20c43e745d3a3d2c710dac86","source":{"kind":"arxiv","id":"2407.03026","version":1},"attestation_state":"computed","paper":{"title":"Qifusion-Net: Layer-adapted Stream/Non-stream Model for End-to-End Multi-Accent Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Haojun Fei, Jingyi Fang, Jinming Chen, Yaoxuan Wang, Yuanzhong Zheng","submitted_at":"2024-07-03T11:35:52Z","abstract_excerpt":"Currently, end-to-end (E2E) speech recognition methods have achieved promising performance. However, auto speech recognition (ASR) models still face challenges in recognizing multi-accent speech accurately. We propose a layer-adapted fusion (LAF) model, called Qifusion-Net, which does not require any prior knowledge about the target accent. Based on dynamic chunk strategy, our approach enables streaming decoding and can extract frame-level acoustic feature, facilitating fine-grained information fusion. Experiment results demonstrate that our proposed methods outperform the baseline with relati"},"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":"2407.03026","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-03T11:35:52Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"e7556173247ba17ecdd2a2cabfbc75d432a430b34043402ea7f0fab2485253ec","abstract_canon_sha256":"0323863a2cf7cc0f8bcce727038593c8ae958b9a102f8bbe87fe53d6f212c201"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:45.266030Z","signature_b64":"j3633y4qp26WZsMK/G8OxXzz82u0JfKjBTaSxvKYjKE45W5ndSBjRXClG9LSVH9LMg0MbQOPyu5qV1BIp9b/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e8332e18d6e81d49749e76b78c3358df5d8c26c20c43e745d3a3d2c710dac86","last_reissued_at":"2026-07-05T08:39:45.265533Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:45.265533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Qifusion-Net: Layer-adapted Stream/Non-stream Model for End-to-End Multi-Accent Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Haojun Fei, Jingyi Fang, Jinming Chen, Yaoxuan Wang, Yuanzhong Zheng","submitted_at":"2024-07-03T11:35:52Z","abstract_excerpt":"Currently, end-to-end (E2E) speech recognition methods have achieved promising performance. However, auto speech recognition (ASR) models still face challenges in recognizing multi-accent speech accurately. We propose a layer-adapted fusion (LAF) model, called Qifusion-Net, which does not require any prior knowledge about the target accent. Based on dynamic chunk strategy, our approach enables streaming decoding and can extract frame-level acoustic feature, facilitating fine-grained information fusion. Experiment results demonstrate that our proposed methods outperform the baseline with relati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03026","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.03026/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":"2407.03026","created_at":"2026-07-05T08:39:45.265595+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.03026v1","created_at":"2026-07-05T08:39:45.265595+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03026","created_at":"2026-07-05T08:39:45.265595+00:00"},{"alias_kind":"pith_short_12","alias_value":"H2BTFYMNN2A5","created_at":"2026-07-05T08:39:45.265595+00:00"},{"alias_kind":"pith_short_16","alias_value":"H2BTFYMNN2A5JF2J","created_at":"2026-07-05T08:39:45.265595+00:00"},{"alias_kind":"pith_short_8","alias_value":"H2BTFYMN","created_at":"2026-07-05T08:39:45.265595+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/H2BTFYMNN2A5JF2J45VXRQZVRX","json":"https://pith.science/pith/H2BTFYMNN2A5JF2J45VXRQZVRX.json","graph_json":"https://pith.science/api/pith-number/H2BTFYMNN2A5JF2J45VXRQZVRX/graph.json","events_json":"https://pith.science/api/pith-number/H2BTFYMNN2A5JF2J45VXRQZVRX/events.json","paper":"https://pith.science/paper/H2BTFYMN"},"agent_actions":{"view_html":"https://pith.science/pith/H2BTFYMNN2A5JF2J45VXRQZVRX","download_json":"https://pith.science/pith/H2BTFYMNN2A5JF2J45VXRQZVRX.json","view_paper":"https://pith.science/paper/H2BTFYMN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.03026&json=true","fetch_graph":"https://pith.science/api/pith-number/H2BTFYMNN2A5JF2J45VXRQZVRX/graph.json","fetch_events":"https://pith.science/api/pith-number/H2BTFYMNN2A5JF2J45VXRQZVRX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H2BTFYMNN2A5JF2J45VXRQZVRX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H2BTFYMNN2A5JF2J45VXRQZVRX/action/storage_attestation","attest_author":"https://pith.science/pith/H2BTFYMNN2A5JF2J45VXRQZVRX/action/author_attestation","sign_citation":"https://pith.science/pith/H2BTFYMNN2A5JF2J45VXRQZVRX/action/citation_signature","submit_replication":"https://pith.science/pith/H2BTFYMNN2A5JF2J45VXRQZVRX/action/replication_record"}},"created_at":"2026-07-05T08:39:45.265595+00:00","updated_at":"2026-07-05T08:39:45.265595+00:00"}