{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:H2BTFYMNN2A5JF2J45VXRQZVRX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0323863a2cf7cc0f8bcce727038593c8ae958b9a102f8bbe87fe53d6f212c201","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-03T11:35:52Z","title_canon_sha256":"e7556173247ba17ecdd2a2cabfbc75d432a430b34043402ea7f0fab2485253ec"},"schema_version":"1.0","source":{"id":"2407.03026","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03026","created_at":"2026-07-05T08:39:45Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03026v1","created_at":"2026-07-05T08:39:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03026","created_at":"2026-07-05T08:39:45Z"},{"alias_kind":"pith_short_12","alias_value":"H2BTFYMNN2A5","created_at":"2026-07-05T08:39:45Z"},{"alias_kind":"pith_short_16","alias_value":"H2BTFYMNN2A5JF2J","created_at":"2026-07-05T08:39:45Z"},{"alias_kind":"pith_short_8","alias_value":"H2BTFYMN","created_at":"2026-07-05T08:39:45Z"}],"graph_snapshots":[{"event_id":"sha256:8dfed424e02d16b8efd7ea62110711b7bddcf85a19e6190b0faec0b9dee2020e","target":"graph","created_at":"2026-07-05T08:39:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.03026/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Haojun Fei, Jingyi Fang, Jinming Chen, Yaoxuan Wang, Yuanzhong Zheng","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-03T11:35:52Z","title":"Qifusion-Net: Layer-adapted Stream/Non-stream Model for End-to-End Multi-Accent Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03026","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ee7143642ad1759286fca3b189c27a3f480de7a4664d0bd36243b66f625aa0f9","target":"record","created_at":"2026-07-05T08:39:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0323863a2cf7cc0f8bcce727038593c8ae958b9a102f8bbe87fe53d6f212c201","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-03T11:35:52Z","title_canon_sha256":"e7556173247ba17ecdd2a2cabfbc75d432a430b34043402ea7f0fab2485253ec"},"schema_version":"1.0","source":{"id":"2407.03026","kind":"arxiv","version":1}},"canonical_sha256":"3e8332e18d6e81d49749e76b78c3358df5d8c26c20c43e745d3a3d2c710dac86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e8332e18d6e81d49749e76b78c3358df5d8c26c20c43e745d3a3d2c710dac86","first_computed_at":"2026-07-05T08:39:45.265533Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:45.265533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j3633y4qp26WZsMK/G8OxXzz82u0JfKjBTaSxvKYjKE45W5ndSBjRXClG9LSVH9LMg0MbQOPyu5qV1BIp9b/Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:45.266030Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.03026","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee7143642ad1759286fca3b189c27a3f480de7a4664d0bd36243b66f625aa0f9","sha256:8dfed424e02d16b8efd7ea62110711b7bddcf85a19e6190b0faec0b9dee2020e"],"state_sha256":"0893f643d9a9ab5e2f187f7169f1120a46287ed91e77ea431c52e10461725add"}