{"id":"W4407719212","doi":"10.1007/978-981-96-2292-4_7","title":"Joint Multi-modal Modeling for Speech-to-Text Translation as Multilingual Neural Machine Translation","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Machine translation; Translation (biology); Natural language processing; Joint (building); Modal; Artificial intelligence; Speech recognition; Engineering; Biology; Chemistry; Messenger RNA; Structural engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077326,0.0008567296,0.0009540701,0.0005342318,0.0005079427,0.001505569,0.001161803,0.001257939,0.005899074],"category_scores_gemma":[0.001773357,0.0005328905,0.001549589,0.001259672,0.0004313446,0.001860499,0.001290837,0.00155513,0.00388752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006886324,"about_ca_system_score_gemma":0.0007247588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004072946,"about_ca_topic_score_gemma":0.007488328,"domain_scores_codex":[0.9994859,0.0001946059,0.00003840553,0.0001288439,0.0001063593,0.00004585179],"domain_scores_gemma":[0.9993099,0.0003735567,0.00004849441,0.0001111231,0.0001360076,0.00002092103],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003117051,0.0001926937,0.0004620359,0.0004319123,0.0002567102,0.0003241352,0.0002503808,0.4212978,0.02345762,0.07657653,0.01563309,0.4608053],"study_design_scores_gemma":[0.000002692724,0.00001826962,0.00009120622,0.00001034845,0.00002151064,0.00005284776,0.00001556134,0.9715356,0.00330606,0.02176226,0.003170269,0.00001344584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004554517,0.001130586,0.9885351,0.0002864625,0.0001478677,0.0000190241,0.0002681991,0.001519393,0.003538816],"genre_scores_gemma":[0.3802156,0.002853081,0.57989,0.0003891125,0.000387812,0.0002485922,0.002618971,0.001248218,0.03214863],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005899074,"threshold_uncertainty_score":0.01973438,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07970553934307349,"score_gpt":0.3535581530429059,"score_spread":0.2738526136998324,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}