{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HDSEELNEAD2DPINO6SRDH6MOFJ","short_pith_number":"pith:HDSEELNE","schema_version":"1.0","canonical_sha256":"38e4422da400f437a1aef4a233f98e2a4d0a401a8ac40ab3cbf2c5e745483f34","source":{"kind":"arxiv","id":"2606.10439","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Multilingual LLM-based ASR with Mixture of Experts and Dynamic Downsampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Guodong Lin, Ke Li, Wei-Qiang Zhang, Yuxiang Fu, Ziqi Chen","submitted_at":"2026-06-09T05:35:31Z","abstract_excerpt":"The rapid progress of large language models (LLMs) has opened up a new frontier for automatic speech recognition (ASR), making their effective integration a critical and challenging research direction. To this end, this work proposes a projector-based LLM-ASR framework targeting the key challenges of multilingual generalization and modality alignment. Our approach incorporates a Mixture of Experts (MoE) architecture to improve cross-lingual adaptability, and a Continuous Integrate-and-Fire (CIF) mechanism for dynamic downsampling and modality alignment. Experimental results show that the combi"},"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":"2606.10439","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-09T05:35:31Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"74ce010423b4d654f074078bc9513bfc5391ab94c6ec1c21f243fcb694b80600","abstract_canon_sha256":"8c0efa27cfccbf1d734395aacf8d17c50ee467bcdf30bbb1e98693aad15c95e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:18.992974Z","signature_b64":"1sqhh7ZmtV+21JcxuvmhmigBTCWvw6Rw75f/LMAOKLsLasDpzbBgI952iYqxeO2Y5wtuL+MYjPoLjvCn0Z8ZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38e4422da400f437a1aef4a233f98e2a4d0a401a8ac40ab3cbf2c5e745483f34","last_reissued_at":"2026-06-10T01:10:18.992120Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:18.992120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Multilingual LLM-based ASR with Mixture of Experts and Dynamic Downsampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Guodong Lin, Ke Li, Wei-Qiang Zhang, Yuxiang Fu, Ziqi Chen","submitted_at":"2026-06-09T05:35:31Z","abstract_excerpt":"The rapid progress of large language models (LLMs) has opened up a new frontier for automatic speech recognition (ASR), making their effective integration a critical and challenging research direction. To this end, this work proposes a projector-based LLM-ASR framework targeting the key challenges of multilingual generalization and modality alignment. Our approach incorporates a Mixture of Experts (MoE) architecture to improve cross-lingual adaptability, and a Continuous Integrate-and-Fire (CIF) mechanism for dynamic downsampling and modality alignment. Experimental results show that the combi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10439","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/2606.10439/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":"2606.10439","created_at":"2026-06-10T01:10:18.992266+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10439v1","created_at":"2026-06-10T01:10:18.992266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10439","created_at":"2026-06-10T01:10:18.992266+00:00"},{"alias_kind":"pith_short_12","alias_value":"HDSEELNEAD2D","created_at":"2026-06-10T01:10:18.992266+00:00"},{"alias_kind":"pith_short_16","alias_value":"HDSEELNEAD2DPINO","created_at":"2026-06-10T01:10:18.992266+00:00"},{"alias_kind":"pith_short_8","alias_value":"HDSEELNE","created_at":"2026-06-10T01:10:18.992266+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/HDSEELNEAD2DPINO6SRDH6MOFJ","json":"https://pith.science/pith/HDSEELNEAD2DPINO6SRDH6MOFJ.json","graph_json":"https://pith.science/api/pith-number/HDSEELNEAD2DPINO6SRDH6MOFJ/graph.json","events_json":"https://pith.science/api/pith-number/HDSEELNEAD2DPINO6SRDH6MOFJ/events.json","paper":"https://pith.science/paper/HDSEELNE"},"agent_actions":{"view_html":"https://pith.science/pith/HDSEELNEAD2DPINO6SRDH6MOFJ","download_json":"https://pith.science/pith/HDSEELNEAD2DPINO6SRDH6MOFJ.json","view_paper":"https://pith.science/paper/HDSEELNE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10439&json=true","fetch_graph":"https://pith.science/api/pith-number/HDSEELNEAD2DPINO6SRDH6MOFJ/graph.json","fetch_events":"https://pith.science/api/pith-number/HDSEELNEAD2DPINO6SRDH6MOFJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HDSEELNEAD2DPINO6SRDH6MOFJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HDSEELNEAD2DPINO6SRDH6MOFJ/action/storage_attestation","attest_author":"https://pith.science/pith/HDSEELNEAD2DPINO6SRDH6MOFJ/action/author_attestation","sign_citation":"https://pith.science/pith/HDSEELNEAD2DPINO6SRDH6MOFJ/action/citation_signature","submit_replication":"https://pith.science/pith/HDSEELNEAD2DPINO6SRDH6MOFJ/action/replication_record"}},"created_at":"2026-06-10T01:10:18.992266+00:00","updated_at":"2026-06-10T01:10:18.992266+00:00"}