{"id":"W310658760","doi":"10.21437/eurospeech.2001-384","title":"Robust automatic speech recognition in low-SNR car environments by the application of a connectionist subspace-based approach to the melbased cepstral coefficients","year":2001,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec","funders":"","keywords":"Computer science; Speech recognition; TIMIT; Robustness (evolution); Pattern recognition (psychology); Cepstrum; Artificial intelligence; Mel-frequency cepstrum; Hidden Markov model; Subspace topology; Noise (video); Multilayer perceptron; Preprocessor; Noise reduction; Speech enhancement; Feature extraction; Artificial neural network","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":[0.0005049916,0.0001362623,0.0001354431,0.00007870387,0.0002176171,0.0001382105,0.0006172369,0.00005245344,0.00001220762],"category_scores_gemma":[0.00003348203,0.00008789527,0.00004518118,0.0007968285,0.0000726998,0.0001732847,0.00005385677,0.0001165728,0.00004685309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009491021,"about_ca_system_score_gemma":0.00005015147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001844369,"about_ca_topic_score_gemma":0.00008933592,"domain_scores_codex":[0.9986247,0.0001017223,0.00027768,0.0003567559,0.0003725885,0.0002665859],"domain_scores_gemma":[0.9992281,0.00008261998,0.0001390705,0.0004585668,0.00003060577,0.00006108535],"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":[0.00007057256,0.002561313,0.006745697,0.0001416392,0.00004179047,0.000005209349,0.001585149,0.08472543,0.05354915,0.0002114323,0.002922046,0.8474405],"study_design_scores_gemma":[0.0008713485,0.00006951465,0.00272336,0.00004551557,0.00001184891,0.00001616753,0.0003151992,0.7423862,0.2524835,0.0001449092,0.0007168329,0.0002156157],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2632539,0.00001734067,0.7342913,0.001079785,0.00004079212,0.0005142392,0.000003627052,0.00004879336,0.0007502213],"genre_scores_gemma":[0.9612672,0.000001927936,0.03785932,0.0005839311,0.00002038782,0.0001150511,0.0000260732,0.000008920931,0.0001172235],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.847225,"threshold_uncertainty_score":0.3584265,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02263769535313786,"score_gpt":0.2236142859068248,"score_spread":0.2009765905536869,"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."}}