{"id":"W2135474356","doi":"10.1109/icassp.2002.5743869","title":"Auditory-based acoustic distinctive features and spectral cues for automatic speech recognition using a multi-stream paradigm","year":2002,"lang":"en","type":"article","venue":"IEEE International Conference on Acoustics Speech and Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Speech recognition; Bigram; Hidden Markov model; TIMIT; Word error rate; Artificial intelligence; Feature extraction; Pattern recognition (psychology)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002114681,0.0003207356,0.000285698,0.0002885903,0.0003484221,0.0008357766,0.0003417827,0.0001439404,0.0001398583],"category_scores_gemma":[0.0001881736,0.0003023378,0.000073916,0.0001544195,0.0001625964,0.0005342643,0.00003878646,0.0002543823,0.00001318076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001119695,"about_ca_system_score_gemma":0.0001111245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001382593,"about_ca_topic_score_gemma":0.00001727887,"domain_scores_codex":[0.9981655,0.00005716149,0.0003550605,0.0006049733,0.0004631063,0.0003542037],"domain_scores_gemma":[0.9986678,0.0003457047,0.0002572289,0.0001369025,0.000408858,0.0001834434],"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":[0.00007292883,0.0003775812,0.00008610531,0.0001877861,0.00006608583,0.00009098449,0.0003102825,0.0002053572,0.03795767,0.0002902085,0.0003324076,0.9600226],"study_design_scores_gemma":[0.000897823,0.0001893028,0.0004932263,0.0004401915,0.00006019868,0.0001843606,0.0001222643,0.9794127,0.01108105,0.006713861,0.00001616819,0.0003887954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1036456,0.00007759076,0.893698,0.0006279801,0.0004712792,0.0003666152,0.0001108165,0.0001847407,0.0008174255],"genre_scores_gemma":[0.7254485,0.00003193459,0.2737992,0.0002814462,0.0002852376,0.0000260593,0.00001469499,0.00001808445,0.00009481802],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9792074,"threshold_uncertainty_score":0.9999429,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09560722869828778,"score_gpt":0.3126416919736763,"score_spread":0.2170344632753885,"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."}}