{"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"}