{"id":"W2036242736","doi":"10.1109/icassp.2013.6638952","title":"A deep convolutional neural network using heterogeneous pooling for trading acoustic invariance with phonetic confusion","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":188,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Word error rate; Speech recognition; Pooling; Convolutional neural network; TIMIT; Artificial intelligence; Dropout (neural networks); Deep learning; Artificial neural network; Hidden Markov model; Pattern recognition (psychology); Machine learning","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001207194,0.000146062,0.0001663284,0.0000565278,0.0002679234,0.0002301759,0.0002815456,0.00005261008,0.000292583],"category_scores_gemma":[0.00003160375,0.0001190004,0.000060531,0.0002059014,0.0000432714,0.0003345381,0.00005273641,0.0000685991,0.00003000575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004418596,"about_ca_system_score_gemma":0.00005173636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005419262,"about_ca_topic_score_gemma":0.00003003511,"domain_scores_codex":[0.9988477,0.0000428021,0.0002047791,0.0003317058,0.0001860578,0.0003870176],"domain_scores_gemma":[0.9991992,0.0002713804,0.00008101507,0.0001909968,0.0001369365,0.0001205025],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001561053,0.0002979954,0.001164795,0.0001456654,0.0002491642,0.00009471588,0.000878106,0.6869699,0.07857637,0.01227973,0.001551208,0.2176362],"study_design_scores_gemma":[0.0003852696,0.00006924124,0.0003254412,0.00003669956,0.00001432629,0.000259199,0.00001996796,0.995303,0.001336793,0.002026483,0.00003265871,0.0001909677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1329963,0.00007070028,0.8657231,0.0001789187,0.0002369028,0.0003811899,7.256913e-7,0.0001182105,0.0002940477],"genre_scores_gemma":[0.6900868,0.000001633815,0.308955,0.0007574912,0.0001097124,0.00003913824,0.000001605464,0.000009776363,0.00003880907],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5570906,"threshold_uncertainty_score":0.4852695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03207903847495538,"score_gpt":0.2313530530693191,"score_spread":0.1992740145943637,"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."}}