{"id":"W4416756303","doi":"10.1109/taslpro.2025.3633090","title":"Towards Effective and Efficient Non-Autoregressive Decoders for Conformer and LLM-Based ASR Using Block-Based Attention Mask","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","keywords":"Decoding methods; Speedup; Inference; Autoregressive model; Connectionism; Language model; Speech processing; Speech coding","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":[0.0006752406,0.0008556157,0.000598044,0.0004086861,0.0002759066,0.0008529112,0.001227008,0.0007303617,0.003223321],"category_scores_gemma":[0.002227355,0.0003796092,0.0004058101,0.0003462693,0.0003411628,0.001263966,0.0009772484,0.001194128,0.002279326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006039963,"about_ca_system_score_gemma":0.001416681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004812035,"about_ca_topic_score_gemma":0.008595301,"domain_scores_codex":[0.9994891,0.0001096807,0.00004213649,0.0001421887,0.0001603399,0.00005648701],"domain_scores_gemma":[0.9993913,0.0002458902,0.00005492949,0.0001011764,0.0001633413,0.00004329236],"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":[0.0005577639,0.0001782843,0.001653251,0.0001370341,0.00009690625,0.0001954499,0.0001853379,0.07216705,0.1705937,0.01605668,0.005593521,0.7325851],"study_design_scores_gemma":[0.00002413881,0.00009999077,0.0003538776,0.00000938155,0.00002284283,0.000116148,0.00002346514,0.9273089,0.06476362,0.003706136,0.003556355,0.00001500526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02471226,0.0003566158,0.9684417,0.0001885438,0.00006722126,0.0000593397,0.0001630116,0.00426036,0.001751019],"genre_scores_gemma":[0.3947755,0.0003120694,0.5955893,0.0003504049,0.00008862565,0.0002299143,0.0009068275,0.00043337,0.0073139],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004812035,"threshold_uncertainty_score":0.01078314,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01155468110483668,"score_gpt":0.279686951037758,"score_spread":0.2681322699329213,"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."}}