{"id":"W1898026345","doi":"10.1109/icassp.1980.1170837","title":"A speaker verification algorithm for speech utterances corrupted by noise with unknown statistics","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Speech recognition; Computer science; Noise (video); Preprocessor; Noise measurement; Algorithm; Speaker verification; Distortion (music); White noise; Speech enhancement; Speaker recognition; Filter (signal processing); Pattern recognition (psychology); Artificial intelligence; Noise reduction","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":[0.0001082718,0.0001235371,0.0001167384,0.00004080674,0.0001180573,0.0002356269,0.0003389948,0.00003292835,0.00003500421],"category_scores_gemma":[0.00001230536,0.0000947398,0.00001772097,0.0002235638,0.00003621434,0.0005254645,0.00002484269,0.00005654537,0.00004873745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003105205,"about_ca_system_score_gemma":0.00006524373,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001202909,"about_ca_topic_score_gemma":0.00002762453,"domain_scores_codex":[0.9990371,0.00001076557,0.0001652426,0.0003287663,0.0002089198,0.0002492034],"domain_scores_gemma":[0.9993759,0.00005309149,0.00008705217,0.0002481801,0.0001593177,0.00007649306],"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":[0.000005991245,0.00004985666,0.00007602805,0.00000771823,0.000007083073,0.000001572725,0.00008849342,0.00001736152,0.002081422,0.0004607203,0.01496234,0.9822414],"study_design_scores_gemma":[0.001361927,0.0002392387,0.0003400574,0.00003542794,0.00001544372,0.00004343258,0.0000304341,0.4116282,0.3499448,0.0007148485,0.2351995,0.000446714],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002240823,0.0001043672,0.9948913,0.001072818,0.00009296384,0.0001945865,0.00002811211,0.0001532352,0.001221797],"genre_scores_gemma":[0.01209869,0.00001308172,0.9838166,0.000958026,0.00009674355,0.00002184981,0.00003203372,0.00001030892,0.002952687],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9817947,"threshold_uncertainty_score":0.3863377,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008503395501873939,"score_gpt":0.2398919580183501,"score_spread":0.2313885625164762,"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."}}