{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Z3ZJ6F7LLSOPJNV5AOXDBWCGMD","short_pith_number":"pith:Z3ZJ6F7L","schema_version":"1.0","canonical_sha256":"cef29f17eb5c9cf4b6bd03ae30d84660e29c930fd3aab039cbca515e862ba24d","source":{"kind":"arxiv","id":"2310.09424","version":1},"attestation_state":"computed","paper":{"title":"SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Andrei Andrusenko, Boris Ginsburg, He Huang, Jagadeesh Balam, Jason Li, Krishna C. Puvvada, Oleksii Hrinchuk, Subhankar Ghosh, Zhehuai Chen","submitted_at":"2023-10-13T22:07:33Z","abstract_excerpt":"We present a novel Speech Augmented Language Model (SALM) with {\\em multitask} and {\\em in-context} learning capabilities. SALM comprises a frozen text LLM, a audio encoder, a modality adapter module, and LoRA layers to accommodate speech input and associated task instructions. The unified SALM not only achieves performance on par with task-specific Conformer baselines for Automatic Speech Recognition (ASR) and Speech Translation (AST), but also exhibits zero-shot in-context learning capabilities, demonstrated through keyword-boosting task for ASR and AST. Moreover, {\\em speech supervised in-c"},"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":"2310.09424","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-13T22:07:33Z","cross_cats_sorted":["cs.HC","cs.SD","eess.AS"],"title_canon_sha256":"cc1aff0c40e24222431cd381d9255e77065bc573d72a0d2d1e449eee97e4c79c","abstract_canon_sha256":"5a128520654090306949affb4cfaa89f53a330b30284d402a77cfe581d76c48b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:47.697878Z","signature_b64":"XSoaPUl+QpkHt0IVauuZVVt0VxAfBhU2YBXpR9fkWJgDvwM4OCnbgG++vSo321e8bEM2EsZiCvX4WTEeRdEOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cef29f17eb5c9cf4b6bd03ae30d84660e29c930fd3aab039cbca515e862ba24d","last_reissued_at":"2026-07-05T07:00:47.697431Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:47.697431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Andrei Andrusenko, Boris Ginsburg, He Huang, Jagadeesh Balam, Jason Li, Krishna C. Puvvada, Oleksii Hrinchuk, Subhankar Ghosh, Zhehuai Chen","submitted_at":"2023-10-13T22:07:33Z","abstract_excerpt":"We present a novel Speech Augmented Language Model (SALM) with {\\em multitask} and {\\em in-context} learning capabilities. SALM comprises a frozen text LLM, a audio encoder, a modality adapter module, and LoRA layers to accommodate speech input and associated task instructions. The unified SALM not only achieves performance on par with task-specific Conformer baselines for Automatic Speech Recognition (ASR) and Speech Translation (AST), but also exhibits zero-shot in-context learning capabilities, demonstrated through keyword-boosting task for ASR and AST. Moreover, {\\em speech supervised in-c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09424","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/2310.09424/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":"2310.09424","created_at":"2026-07-05T07:00:47.697488+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.09424v1","created_at":"2026-07-05T07:00:47.697488+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09424","created_at":"2026-07-05T07:00:47.697488+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z3ZJ6F7LLSOP","created_at":"2026-07-05T07:00:47.697488+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z3ZJ6F7LLSOPJNV5","created_at":"2026-07-05T07:00:47.697488+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z3ZJ6F7L","created_at":"2026-07-05T07:00:47.697488+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08486","citing_title":"TRADE: Transducer-Augmented Decoder for Speech LLM","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11219","citing_title":"Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11769","citing_title":"Safety-Oriented Evaluation of Language Understanding Systems for Air Traffic Control","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09332","citing_title":"Phonemes vs. Projectors: An Investigation of Speech-Language Interfaces for LLM-based ASR","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z3ZJ6F7LLSOPJNV5AOXDBWCGMD","json":"https://pith.science/pith/Z3ZJ6F7LLSOPJNV5AOXDBWCGMD.json","graph_json":"https://pith.science/api/pith-number/Z3ZJ6F7LLSOPJNV5AOXDBWCGMD/graph.json","events_json":"https://pith.science/api/pith-number/Z3ZJ6F7LLSOPJNV5AOXDBWCGMD/events.json","paper":"https://pith.science/paper/Z3ZJ6F7L"},"agent_actions":{"view_html":"https://pith.science/pith/Z3ZJ6F7LLSOPJNV5AOXDBWCGMD","download_json":"https://pith.science/pith/Z3ZJ6F7LLSOPJNV5AOXDBWCGMD.json","view_paper":"https://pith.science/paper/Z3ZJ6F7L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.09424&json=true","fetch_graph":"https://pith.science/api/pith-number/Z3ZJ6F7LLSOPJNV5AOXDBWCGMD/graph.json","fetch_events":"https://pith.science/api/pith-number/Z3ZJ6F7LLSOPJNV5AOXDBWCGMD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z3ZJ6F7LLSOPJNV5AOXDBWCGMD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z3ZJ6F7LLSOPJNV5AOXDBWCGMD/action/storage_attestation","attest_author":"https://pith.science/pith/Z3ZJ6F7LLSOPJNV5AOXDBWCGMD/action/author_attestation","sign_citation":"https://pith.science/pith/Z3ZJ6F7LLSOPJNV5AOXDBWCGMD/action/citation_signature","submit_replication":"https://pith.science/pith/Z3ZJ6F7LLSOPJNV5AOXDBWCGMD/action/replication_record"}},"created_at":"2026-07-05T07:00:47.697488+00:00","updated_at":"2026-07-05T07:00:47.697488+00:00"}