{"id":"W1996941879","doi":"10.1121/1.4781999","title":"Efficient spectral measures for automatic speech recognition","year":2007,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Spectrogram; Computer science; Speech recognition; Spectral envelope; Mel-frequency cepstrum; Linear prediction; Cepstrum; Wideband; Wavelet; Acoustics; Bandwidth (computing); Pattern recognition (psychology); Artificial intelligence; Feature extraction; Telecommunications","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002285861,0.0001076195,0.0002418255,0.00003032202,0.0001886362,0.00003039568,0.0009128144,0.00005226864,0.00003586676],"category_scores_gemma":[0.0005863752,0.00005587472,0.0005357077,0.0003467248,0.0002757573,0.00006032442,0.00008999465,0.0002342902,0.000008632635],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007156893,"about_ca_system_score_gemma":0.00007816647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007832949,"about_ca_topic_score_gemma":4.419949e-7,"domain_scores_codex":[0.9984236,0.0001139098,0.0004874827,0.00008998068,0.0006192575,0.0002658139],"domain_scores_gemma":[0.9973425,0.001471022,0.0004942812,0.0002698487,0.0003334532,0.00008892759],"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":[0.00005053883,0.0001798957,0.000009019331,0.00002519701,0.0001082779,0.000001178538,0.0005268442,0.0003357291,0.01098059,0.00001341825,0.00815228,0.9796171],"study_design_scores_gemma":[0.0006663406,0.0004121932,0.001603494,0.0001437723,0.0002708613,0.0003305575,0.001422564,0.9270935,0.05892127,0.007835225,0.001109882,0.0001903209],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03158097,0.00006980095,0.9633614,0.004197464,0.0003274372,0.0001747381,0.000003836034,0.00002179538,0.0002625341],"genre_scores_gemma":[0.2463844,0.00004236388,0.7520276,0.001321999,0.000186596,9.66363e-7,1.293334e-7,0.000008204046,0.00002776216],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9794267,"threshold_uncertainty_score":0.2278505,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02682802096998669,"score_gpt":0.2669700108464535,"score_spread":0.2401419898764668,"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."}}