{"id":"W2165712617","doi":"10.1109/tasl.2007.914114","title":"Capturing Local Variability for Speaker Normalization in Speech Recognition","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Hidden Markov model; Normalization (sociology); Image warping; Speech recognition; Computer science; Dynamic time warping; Artificial intelligence; Pattern recognition (psychology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001227272,0.0006729134,0.0007751863,0.0003976323,0.0003188486,0.0007122546,0.0007986721,0.0005568869,0.00131943],"category_scores_gemma":[0.002696616,0.0003438739,0.0008803827,0.0006261381,0.0006466619,0.001146508,0.0008223911,0.001297488,0.0009183502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004095639,"about_ca_system_score_gemma":0.0006324707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001933792,"about_ca_topic_score_gemma":0.004004418,"domain_scores_codex":[0.9992872,0.0002603582,0.00002678006,0.0001662626,0.0002151456,0.00004425682],"domain_scores_gemma":[0.9993089,0.0003740868,0.00005974776,0.0001551943,0.00008367353,0.00001833429],"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":[0.000288448,0.00009099125,0.001968548,0.000183222,0.0002040189,0.0001868052,0.0004191921,0.4545448,0.06233378,0.02223785,0.002633787,0.4549084],"study_design_scores_gemma":[0.000005654617,0.00007733579,0.001247464,0.00001364568,0.00004553548,0.0001424541,0.00003643544,0.9759358,0.01003388,0.00966815,0.002764244,0.0000295662],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01023447,0.000317754,0.9883391,0.00007626315,0.0000315965,0.00001882161,0.00004569019,0.0003788244,0.0005574744],"genre_scores_gemma":[0.5785803,0.001336556,0.4131976,0.0001659181,0.0002021137,0.0002805554,0.0005878123,0.0004028106,0.005246383],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001933792,"threshold_uncertainty_score":0.006490529,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02366902432876057,"score_gpt":0.2478770694418866,"score_spread":0.2242080451131261,"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."}}