{"id":"W1498991127","doi":"10.1186/s13634-015-0238-6","title":"Speech recognition in reverberant and noisy environments employing multiple feature extractors and i-vector speaker adaptation","year":2015,"lang":"en","type":"article","venue":"EURASIP Journal on Advances in Signal Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Speech recognition; Filter bank; Word error rate; Speaker recognition; Reverberation; Microphone; Channel (broadcasting); Word (group theory); Speech processing; Pattern recognition (psychology); Artificial intelligence; Mathematics","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":[0.0007605696,0.0002234259,0.0002382496,0.0002916674,0.0001734445,0.000429162,0.0002026961,0.0000813338,0.000001971198],"category_scores_gemma":[0.0001866,0.0001967277,0.00002368615,0.0003821403,0.00006017033,0.004244139,0.00006029211,0.0006313891,0.000007200845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001702133,"about_ca_system_score_gemma":0.00008513542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004434956,"about_ca_topic_score_gemma":0.00003214847,"domain_scores_codex":[0.9982765,0.0001271077,0.0003864137,0.0004231148,0.000442483,0.0003443673],"domain_scores_gemma":[0.9992065,0.0001298203,0.0003275013,0.00008415814,0.00005336665,0.0001986632],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00010676,0.00007219065,0.01512085,0.00004069455,0.000002558778,0.0002259681,0.001515273,0.0009764015,0.005389011,0.000001628922,0.000009276885,0.9765394],"study_design_scores_gemma":[0.02986218,0.003326588,0.3026057,0.0199552,0.00008870733,0.0102526,0.01037033,0.2784395,0.2619442,0.06189387,0.01558242,0.005678691],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7976786,0.01417172,0.1866747,0.0006153368,0.0002723431,0.0002087188,0.000001786278,0.00004236737,0.0003343702],"genre_scores_gemma":[0.9002968,0.0006375358,0.09864528,0.0002277955,0.0001396767,0.000003837405,0.000001672241,0.00001743818,0.00002993995],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9708607,"threshold_uncertainty_score":0.8022322,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03644563081396488,"score_gpt":0.2734832760116827,"score_spread":0.2370376451977178,"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."}}