{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4EL5ZDPVCBGDJRR64VIEWHU4JV","short_pith_number":"pith:4EL5ZDPV","schema_version":"1.0","canonical_sha256":"e117dc8df5104c34c63ee5504b1e9c4d70d61737dcaf6d153527d36497c30dc5","source":{"kind":"arxiv","id":"2412.11538","version":3},"attestation_state":"computed","paper":{"title":"MERaLiON-SpeechEncoder: Towards a Speech Foundation Model for Singapore and Beyond","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ai Ti Aw, Geyu Lin, Hardik B. Sailor, Jeremy H. M. Wong, Jinyang Wu, Kye Min Tan, Muhammad Huzaifah, Nancy F. Chen, Qiongqiong Wang, Tarun K. Vangani, Tianchi Liu","submitted_at":"2024-12-16T08:15:19Z","abstract_excerpt":"This technical report describes the MERaLiON-SpeechEncoder, a foundation model designed to support a wide range of downstream speech applications. Developed as part of Singapore's National Multimodal Large Language Model Programme, the MERaLiON-SpeechEncoder is tailored to address the speech processing needs in Singapore and the surrounding Southeast Asian region. The model currently supports mainly English, including the variety spoken in Singapore. We are actively expanding our datasets to gradually cover other languages in subsequent releases. The MERaLiON-SpeechEncoder was pre-trained from"},"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":"2412.11538","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T08:15:19Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"ba4aff19d75ccaa9659a84a66eb4116c3998611d087adb145c9b5f2ffa59a709","abstract_canon_sha256":"65b621a76cd2d7237f0f4d7e2a4b8530f57fe1afdb2aed085ee8b92602f6b4ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:11.988239Z","signature_b64":"so09SuWYQ5WHxoZsTNExdyaIshD/Ts57tW36roND6MdAYkasTLMtEPdRWDYwuk0nzYgA3EuoGMJSgXVOaTevCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e117dc8df5104c34c63ee5504b1e9c4d70d61737dcaf6d153527d36497c30dc5","last_reissued_at":"2026-07-05T12:09:11.987749Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:11.987749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MERaLiON-SpeechEncoder: Towards a Speech Foundation Model for Singapore and Beyond","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ai Ti Aw, Geyu Lin, Hardik B. Sailor, Jeremy H. M. Wong, Jinyang Wu, Kye Min Tan, Muhammad Huzaifah, Nancy F. Chen, Qiongqiong Wang, Tarun K. Vangani, Tianchi Liu","submitted_at":"2024-12-16T08:15:19Z","abstract_excerpt":"This technical report describes the MERaLiON-SpeechEncoder, a foundation model designed to support a wide range of downstream speech applications. Developed as part of Singapore's National Multimodal Large Language Model Programme, the MERaLiON-SpeechEncoder is tailored to address the speech processing needs in Singapore and the surrounding Southeast Asian region. The model currently supports mainly English, including the variety spoken in Singapore. We are actively expanding our datasets to gradually cover other languages in subsequent releases. The MERaLiON-SpeechEncoder was pre-trained from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11538","kind":"arxiv","version":3},"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/2412.11538/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":"2412.11538","created_at":"2026-07-05T12:09:11.987809+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11538v3","created_at":"2026-07-05T12:09:11.987809+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11538","created_at":"2026-07-05T12:09:11.987809+00:00"},{"alias_kind":"pith_short_12","alias_value":"4EL5ZDPVCBGD","created_at":"2026-07-05T12:09:11.987809+00:00"},{"alias_kind":"pith_short_16","alias_value":"4EL5ZDPVCBGDJRR6","created_at":"2026-07-05T12:09:11.987809+00:00"},{"alias_kind":"pith_short_8","alias_value":"4EL5ZDPV","created_at":"2026-07-05T12:09:11.987809+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/4EL5ZDPVCBGDJRR64VIEWHU4JV","json":"https://pith.science/pith/4EL5ZDPVCBGDJRR64VIEWHU4JV.json","graph_json":"https://pith.science/api/pith-number/4EL5ZDPVCBGDJRR64VIEWHU4JV/graph.json","events_json":"https://pith.science/api/pith-number/4EL5ZDPVCBGDJRR64VIEWHU4JV/events.json","paper":"https://pith.science/paper/4EL5ZDPV"},"agent_actions":{"view_html":"https://pith.science/pith/4EL5ZDPVCBGDJRR64VIEWHU4JV","download_json":"https://pith.science/pith/4EL5ZDPVCBGDJRR64VIEWHU4JV.json","view_paper":"https://pith.science/paper/4EL5ZDPV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11538&json=true","fetch_graph":"https://pith.science/api/pith-number/4EL5ZDPVCBGDJRR64VIEWHU4JV/graph.json","fetch_events":"https://pith.science/api/pith-number/4EL5ZDPVCBGDJRR64VIEWHU4JV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4EL5ZDPVCBGDJRR64VIEWHU4JV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4EL5ZDPVCBGDJRR64VIEWHU4JV/action/storage_attestation","attest_author":"https://pith.science/pith/4EL5ZDPVCBGDJRR64VIEWHU4JV/action/author_attestation","sign_citation":"https://pith.science/pith/4EL5ZDPVCBGDJRR64VIEWHU4JV/action/citation_signature","submit_replication":"https://pith.science/pith/4EL5ZDPVCBGDJRR64VIEWHU4JV/action/replication_record"}},"created_at":"2026-07-05T12:09:11.987809+00:00","updated_at":"2026-07-05T12:09:11.987809+00:00"}