{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:26SV2GCAD63ZWQ4J7SXEXTOBSK","short_pith_number":"pith:26SV2GCA","schema_version":"1.0","canonical_sha256":"d7a55d18401fb79b4389fcae4bcdc1929e110732e0cb1e013464b673b6bc3178","source":{"kind":"arxiv","id":"2507.18051","version":1},"attestation_state":"computed","paper":{"title":"The TEA-ASLP System for Multilingual Conversational Speech Recognition and Speech Diarization in MLC-SLM 2025 Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hongfei Xue, Kaixun Huang, Shen Huang, ShiDong Shang, Zhikai Zhou","submitted_at":"2025-07-24T02:56:29Z","abstract_excerpt":"This paper presents the TEA-ASLP's system submitted to the MLC-SLM 2025 Challenge, addressing multilingual conversational automatic speech recognition (ASR) in Task I and speech diarization ASR in Task II. For Task I, we enhance Ideal-LLM model by integrating known language identification and a multilingual MOE LoRA structure, along with using CTC-predicted tokens as prompts to improve autoregressive generation. The model is trained on approximately 180k hours of multilingual ASR data. In Task II, we replace the baseline English-Chinese speaker diarization model with a more suitable English-on"},"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":"2507.18051","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-24T02:56:29Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"e70133f322f3a9dbcc477dcc816b5884e073d501f531de6123192c723cc8c332","abstract_canon_sha256":"b49c7e9f7277cf8c37b46e1a5c203824a77309c9489a875e433f0bf98fe1bb7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:40.222527Z","signature_b64":"LWA94MGHljnL/1cty5HJA+rLSWSQ8QgFmimJJRkk2/1BtV0q5D/a2mKPurMppvqq7lzePaQnflJZKXSX9nr0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7a55d18401fb79b4389fcae4bcdc1929e110732e0cb1e013464b673b6bc3178","last_reissued_at":"2026-07-05T11:42:40.222065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:40.222065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The TEA-ASLP System for Multilingual Conversational Speech Recognition and Speech Diarization in MLC-SLM 2025 Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hongfei Xue, Kaixun Huang, Shen Huang, ShiDong Shang, Zhikai Zhou","submitted_at":"2025-07-24T02:56:29Z","abstract_excerpt":"This paper presents the TEA-ASLP's system submitted to the MLC-SLM 2025 Challenge, addressing multilingual conversational automatic speech recognition (ASR) in Task I and speech diarization ASR in Task II. For Task I, we enhance Ideal-LLM model by integrating known language identification and a multilingual MOE LoRA structure, along with using CTC-predicted tokens as prompts to improve autoregressive generation. The model is trained on approximately 180k hours of multilingual ASR data. In Task II, we replace the baseline English-Chinese speaker diarization model with a more suitable English-on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18051","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/2507.18051/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":"2507.18051","created_at":"2026-07-05T11:42:40.222132+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.18051v1","created_at":"2026-07-05T11:42:40.222132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18051","created_at":"2026-07-05T11:42:40.222132+00:00"},{"alias_kind":"pith_short_12","alias_value":"26SV2GCAD63Z","created_at":"2026-07-05T11:42:40.222132+00:00"},{"alias_kind":"pith_short_16","alias_value":"26SV2GCAD63ZWQ4J","created_at":"2026-07-05T11:42:40.222132+00:00"},{"alias_kind":"pith_short_8","alias_value":"26SV2GCA","created_at":"2026-07-05T11:42:40.222132+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.18051","citing_title":"The TEA-ASLP System for Multilingual Conversational Speech Recognition and Speech Diarization in MLC-SLM 2025 Challenge","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/26SV2GCAD63ZWQ4J7SXEXTOBSK","json":"https://pith.science/pith/26SV2GCAD63ZWQ4J7SXEXTOBSK.json","graph_json":"https://pith.science/api/pith-number/26SV2GCAD63ZWQ4J7SXEXTOBSK/graph.json","events_json":"https://pith.science/api/pith-number/26SV2GCAD63ZWQ4J7SXEXTOBSK/events.json","paper":"https://pith.science/paper/26SV2GCA"},"agent_actions":{"view_html":"https://pith.science/pith/26SV2GCAD63ZWQ4J7SXEXTOBSK","download_json":"https://pith.science/pith/26SV2GCAD63ZWQ4J7SXEXTOBSK.json","view_paper":"https://pith.science/paper/26SV2GCA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.18051&json=true","fetch_graph":"https://pith.science/api/pith-number/26SV2GCAD63ZWQ4J7SXEXTOBSK/graph.json","fetch_events":"https://pith.science/api/pith-number/26SV2GCAD63ZWQ4J7SXEXTOBSK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/26SV2GCAD63ZWQ4J7SXEXTOBSK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/26SV2GCAD63ZWQ4J7SXEXTOBSK/action/storage_attestation","attest_author":"https://pith.science/pith/26SV2GCAD63ZWQ4J7SXEXTOBSK/action/author_attestation","sign_citation":"https://pith.science/pith/26SV2GCAD63ZWQ4J7SXEXTOBSK/action/citation_signature","submit_replication":"https://pith.science/pith/26SV2GCAD63ZWQ4J7SXEXTOBSK/action/replication_record"}},"created_at":"2026-07-05T11:42:40.222132+00:00","updated_at":"2026-07-05T11:42:40.222132+00:00"}