{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F254GRH5MEYKHJA2ZR5GGS5VG3","short_pith_number":"pith:F254GRH5","schema_version":"1.0","canonical_sha256":"2ebbc344fd6130a3a41acc7a634bb536c104a2d20204329ed692bb30088f814d","source":{"kind":"arxiv","id":"2507.03343","version":2},"attestation_state":"computed","paper":{"title":"SHNU Multilingual Conversational Speech Recognition System for INTERSPEECH 2025 MLC-SLM Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Dongxing Xu, Yanhua Long, Yuang Zheng, Yuxiang Mei","submitted_at":"2025-07-04T07:10:33Z","abstract_excerpt":"This paper describes SHNU multilingual conversational speech recognition system (SHNU-mASR, team name-\"maybe\"), submitted to Track 1 of the INTERSPEECH 2025 MLC-SLM Challenge. Our system integrates a parallel-speech-encoder architecture with a large language model (LLM) to form a unified multilingual ASR framework. The parallel-speech-encoder consists of two pre-trained encoders, the Whisper-large-v3 encoder and mHuBERT-147 encoder. Their output embeddings are concatenated and fed into the LLM, enabling the model to leverage complementary acoustic and linguistic knowledge and achieve competiti"},"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":"2507.03343","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-04T07:10:33Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"626548ec3bb3be1008b483ca2f3bf916965350e8316d0cb7a9ff600bf7c81dc5","abstract_canon_sha256":"c110a1446a896a880368a64069118249ab5166f68b3526339aa2eb52d8e97e15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:26.202102Z","signature_b64":"c3sn/Ow+D7ycf456Mqb/FJntyEKL8Gw5LlWRY8mLVW8vc0VW2tETqArCMc8uOEVyr7xRm35W4KO/MEQB5tCxAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ebbc344fd6130a3a41acc7a634bb536c104a2d20204329ed692bb30088f814d","last_reissued_at":"2026-07-05T11:33:26.201615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:26.201615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SHNU Multilingual Conversational Speech Recognition System for INTERSPEECH 2025 MLC-SLM Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Dongxing Xu, Yanhua Long, Yuang Zheng, Yuxiang Mei","submitted_at":"2025-07-04T07:10:33Z","abstract_excerpt":"This paper describes SHNU multilingual conversational speech recognition system (SHNU-mASR, team name-\"maybe\"), submitted to Track 1 of the INTERSPEECH 2025 MLC-SLM Challenge. Our system integrates a parallel-speech-encoder architecture with a large language model (LLM) to form a unified multilingual ASR framework. The parallel-speech-encoder consists of two pre-trained encoders, the Whisper-large-v3 encoder and mHuBERT-147 encoder. Their output embeddings are concatenated and fed into the LLM, enabling the model to leverage complementary acoustic and linguistic knowledge and achieve competiti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03343","kind":"arxiv","version":2},"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/2507.03343/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":"2507.03343","created_at":"2026-07-05T11:33:26.201683+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.03343v2","created_at":"2026-07-05T11:33:26.201683+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03343","created_at":"2026-07-05T11:33:26.201683+00:00"},{"alias_kind":"pith_short_12","alias_value":"F254GRH5MEYK","created_at":"2026-07-05T11:33:26.201683+00:00"},{"alias_kind":"pith_short_16","alias_value":"F254GRH5MEYKHJA2","created_at":"2026-07-05T11:33:26.201683+00:00"},{"alias_kind":"pith_short_8","alias_value":"F254GRH5","created_at":"2026-07-05T11:33:26.201683+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/F254GRH5MEYKHJA2ZR5GGS5VG3","json":"https://pith.science/pith/F254GRH5MEYKHJA2ZR5GGS5VG3.json","graph_json":"https://pith.science/api/pith-number/F254GRH5MEYKHJA2ZR5GGS5VG3/graph.json","events_json":"https://pith.science/api/pith-number/F254GRH5MEYKHJA2ZR5GGS5VG3/events.json","paper":"https://pith.science/paper/F254GRH5"},"agent_actions":{"view_html":"https://pith.science/pith/F254GRH5MEYKHJA2ZR5GGS5VG3","download_json":"https://pith.science/pith/F254GRH5MEYKHJA2ZR5GGS5VG3.json","view_paper":"https://pith.science/paper/F254GRH5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.03343&json=true","fetch_graph":"https://pith.science/api/pith-number/F254GRH5MEYKHJA2ZR5GGS5VG3/graph.json","fetch_events":"https://pith.science/api/pith-number/F254GRH5MEYKHJA2ZR5GGS5VG3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F254GRH5MEYKHJA2ZR5GGS5VG3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F254GRH5MEYKHJA2ZR5GGS5VG3/action/storage_attestation","attest_author":"https://pith.science/pith/F254GRH5MEYKHJA2ZR5GGS5VG3/action/author_attestation","sign_citation":"https://pith.science/pith/F254GRH5MEYKHJA2ZR5GGS5VG3/action/citation_signature","submit_replication":"https://pith.science/pith/F254GRH5MEYKHJA2ZR5GGS5VG3/action/replication_record"}},"created_at":"2026-07-05T11:33:26.201683+00:00","updated_at":"2026-07-05T11:33:26.201683+00:00"}