{"id":"W2978471304","doi":"10.1109/ism.workshops.2007.47","title":"Evaluation of Speech Enhancement Techniques for Speaker Identification in Noisy Environments","year":2007,"lang":"en","type":"article","venue":"Ninth IEEE International Symposium on Multimedia Workshops (ISMW 2007)","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Speech recognition; Computer science; TIMIT; Speech enhancement; Speaker identification; Noise (video); Speaker recognition; Identification (biology); Background noise; Noise measurement; Speech processing; Voice activity detection; SIGNAL (programming language); Linear predictive coding; Artificial intelligence; Hidden Markov model; Noise reduction; Telecommunications","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":[0.0042547,0.0002285109,0.0002148764,0.0003747522,0.00006395204,0.00009360606,0.0008603976,0.0001566004,0.00009913092],"category_scores_gemma":[0.0002575454,0.0002350736,0.00009932237,0.0002919975,0.00007020377,0.0005321727,0.00007359149,0.0001911104,0.00006737182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000676683,"about_ca_system_score_gemma":0.00007655051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001753534,"about_ca_topic_score_gemma":0.00003250657,"domain_scores_codex":[0.9963463,0.00007489783,0.0008382975,0.0006077325,0.001762641,0.0003701228],"domain_scores_gemma":[0.9983367,0.0002736045,0.0004805342,0.0004069636,0.0004098718,0.00009231908],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008494237,0.000421549,0.000969036,0.00001124557,0.00004476444,0.000004290706,0.0004321248,0.0009924833,0.3131103,0.00009646158,0.0006549757,0.6831778],"study_design_scores_gemma":[0.0009937184,0.00007852039,0.004477428,0.0001644548,0.00002185639,0.000003666871,0.00003357667,0.06207464,0.9285636,0.0004881823,0.002873691,0.0002266716],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09513606,0.0000865805,0.8949141,0.001320843,0.002927228,0.001235461,0.00001171991,0.00007592176,0.004292083],"genre_scores_gemma":[0.8741075,0.00005657537,0.1240387,0.0002753897,0.0005979848,0.0001897006,0.00005841916,0.00002498688,0.0006507384],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7789715,"threshold_uncertainty_score":0.9586022,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03098980943056425,"score_gpt":0.3294634519440112,"score_spread":0.2984736425134469,"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."}}