{"id":"W2160978380","doi":"10.1109/icassp.2007.366915","title":"Integration of Multiple Feature Sets for Reducing Ambiguity in ASR","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"University of Edinburgh","keywords":"Mel-frequency cepstrum; Hidden Markov model; Speech recognition; Computer science; Ambiguity; Feature (linguistics); Pattern recognition (psychology); Phone; Cepstrum; Feature extraction; Artificial intelligence; Artificial neural network","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":[0.000523129,0.0000476977,0.00008213403,0.0001130892,0.00002173171,0.00001424746,0.0001594973,0.00005109467,0.00001441696],"category_scores_gemma":[0.0002722801,0.00003966615,0.00003992888,0.0002043712,0.000009218819,0.0001634849,0.00002297015,0.00004893753,0.000004041208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002485915,"about_ca_system_score_gemma":0.00001659042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001154616,"about_ca_topic_score_gemma":0.000789725,"domain_scores_codex":[0.9995055,0.00001485608,0.0001379711,0.0001414519,0.00008783977,0.0001123433],"domain_scores_gemma":[0.9995013,0.0002115037,0.00004314827,0.0001440601,0.00007228563,0.00002770067],"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":[0.0000149787,0.00006548286,0.0006824253,0.000009925606,0.00000299733,0.000001611219,0.0004337588,0.000003390108,0.04335422,0.002565611,0.001658597,0.951207],"study_design_scores_gemma":[0.0004784421,0.00004959885,0.05164634,0.00005149387,0.000001921841,0.000005329535,0.0002212675,0.08117422,0.8629351,0.002281122,0.001037784,0.0001174335],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1611973,0.0000113633,0.8326328,0.0004916678,0.0001394598,0.0001575942,0.000001945872,0.00004507698,0.005322773],"genre_scores_gemma":[0.6436312,0.000001729205,0.3560187,0.00009933933,0.00001093892,0.000003755775,0.00000197266,0.000001791575,0.0002306027],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9510896,"threshold_uncertainty_score":0.1617539,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04468577413315181,"score_gpt":0.3061615793647963,"score_spread":0.2614758052316444,"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."}}