{"id":"W2038598237","doi":"10.1109/asru.2013.6707717","title":"Cross-lingual context sharing and parameter-tying for multi-lingual speech recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Speech recognition; Context (archaeology); Tying; Natural language processing; Artificial intelligence; Subspace topology; Covariance; Language model; Task (project management); Dialog box","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":[0.002223525,0.0008607428,0.001016101,0.000802877,0.0008636506,0.001260004,0.001207576,0.0009114583,0.00260667],"category_scores_gemma":[0.006014921,0.0005613463,0.001044184,0.001299838,0.0008101533,0.002470568,0.003274563,0.001424354,0.002136414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000360774,"about_ca_system_score_gemma":0.001155714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002171437,"about_ca_topic_score_gemma":0.004395658,"domain_scores_codex":[0.9980217,0.0008105338,0.0001079212,0.0006664689,0.0002720612,0.0001213313],"domain_scores_gemma":[0.9974332,0.000754197,0.0001622103,0.001288999,0.000297447,0.00006386542],"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":[0.0003218454,0.0001653183,0.003794961,0.0001526677,0.0001836781,0.0003297723,0.0006398454,0.09554506,0.04795409,0.01222498,0.002660766,0.836027],"study_design_scores_gemma":[0.00002454294,0.0001959689,0.003746012,0.00004095993,0.0001058226,0.0006179479,0.000407204,0.9046036,0.05018561,0.02784646,0.01211596,0.000109907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02243697,0.0004501151,0.9738705,0.00009409263,0.00006896455,0.00003603719,0.0001395787,0.001530448,0.001373319],"genre_scores_gemma":[0.4951929,0.0006255677,0.4988311,0.0002030504,0.0001765767,0.0002009715,0.001101767,0.0006748217,0.00299339],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00260667,"threshold_uncertainty_score":0.01175922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1231229746230572,"score_gpt":0.3351410842406935,"score_spread":0.2120181096176363,"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."}}