{"id":"W2082864603","doi":"10.1109/icassp.2013.6639018","title":"Efficient manifold learning for speech recognition using locality sensitive hashing","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Locality-sensitive hashing; Nonlinear dimensionality reduction; Discriminative model; Hash function; Speech recognition; Feature vector; Locality; Pattern recognition (psychology); Linear discriminant analysis; Artificial intelligence; Word (group theory); Feature (linguistics); Computation; Computational complexity theory; Dimensionality reduction; Machine learning; Hash table; Algorithm; Mathematics","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":[0.0003510847,0.0001182016,0.000131376,0.00007271062,0.0002047228,0.0002105492,0.0001783884,0.00005544772,0.00001833467],"category_scores_gemma":[0.00017924,0.0001063777,0.00006763868,0.0002257295,0.00002036169,0.0005521252,0.0001420833,0.0001398314,0.00005731651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007717718,"about_ca_system_score_gemma":0.00002146699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001289998,"about_ca_topic_score_gemma":0.000001508083,"domain_scores_codex":[0.9989735,0.00005484544,0.0001922163,0.0003436155,0.0001587437,0.0002770528],"domain_scores_gemma":[0.9991827,0.0001641997,0.00008873573,0.0001795531,0.0003206877,0.00006409445],"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":[0.00000910333,0.00006104111,0.00006179019,0.00003396379,0.00001332722,0.00001159148,0.0002428858,0.001131681,0.04619438,0.001829904,0.0002361401,0.9501742],"study_design_scores_gemma":[0.0001162386,0.00006684315,0.00008874739,0.000033101,0.000003947732,0.00002091694,0.00008988857,0.6314675,0.3621304,0.005640888,0.0001853506,0.0001561435],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06913073,0.00001088163,0.9285797,0.0001416629,0.00007221462,0.0004791243,6.625821e-7,0.0004465096,0.00113846],"genre_scores_gemma":[0.4982978,0.000001996074,0.5013235,0.0002135498,0.00003774849,0.00001049351,0.000002136529,0.000007203834,0.000105635],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.950018,"threshold_uncertainty_score":0.4337957,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0460354194117432,"score_gpt":0.300056680558016,"score_spread":0.2540212611462728,"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."}}