{"id":"W2096958852","doi":"10.1109/itng.2009.332","title":"Feature Combination Using Multiple Spectral Cues for Robust Speech Recognition in Mobile Communications","year":2009,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Speech recognition; Mel-frequency cepstrum; GSM; Feature (linguistics); Front and back ends; Speech processing; Feature extraction; Task (project management); Cepstrum; Artificial intelligence; Mobile telephony; Voice activity detection; Pattern recognition (psychology); Mobile radio; Engineering; 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":[0.0002738004,0.0001055488,0.0001342527,0.000208191,0.0001470589,0.0001360147,0.0005005374,0.00008626428,0.00002673333],"category_scores_gemma":[0.0001020801,0.0001058677,0.0000714508,0.0003949813,0.0000231066,0.0006142154,0.00004571303,0.0001174252,0.00002323676],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009090237,"about_ca_system_score_gemma":0.00003012807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002726963,"about_ca_topic_score_gemma":0.0002478349,"domain_scores_codex":[0.9992034,0.00006115055,0.0001712304,0.0002384231,0.0001259698,0.0001997928],"domain_scores_gemma":[0.9990801,0.0002052334,0.00006891041,0.0004596987,0.0001382339,0.00004781663],"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":[0.0000105054,0.0004242435,0.0004559054,0.000006021771,0.000005494405,0.000001758754,0.0001798779,0.00004275334,0.004088608,0.001735864,0.0009646422,0.9920843],"study_design_scores_gemma":[0.001553803,0.0002229391,0.005958376,0.00007781271,0.0000125697,0.00004368669,0.0002768407,0.8989129,0.06656939,0.02353866,0.002429815,0.0004031848],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2036428,0.000181391,0.7780221,0.007409777,0.0002558421,0.001516856,0.00002284518,0.0004423046,0.00850614],"genre_scores_gemma":[0.3018029,0.000047194,0.6974986,0.0003753376,0.00002583595,0.00003821228,0.00004556968,0.000005330141,0.0001610109],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9916812,"threshold_uncertainty_score":0.4317158,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08309602341530054,"score_gpt":0.3026384742026821,"score_spread":0.2195424507873816,"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."}}