{"id":"W4298028408","doi":"10.48550/arxiv.1803.02551","title":"Extracting Domain Invariant Features by Unsupervised Learning for Robust\\n Automatic Speech Recognition","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Autoencoder; Computer science; Robustness (evolution); Invariant (physics); Speech recognition; Word error rate; Artificial intelligence; Pattern recognition (psychology); Latent variable; Encoder; Domain (mathematical analysis); Deep learning; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007430235,0.0005898345,0.0005072803,0.0007549177,0.0002587815,0.0004559298,0.0006607343,0.0004638094,0.0008755712],"category_scores_gemma":[0.002071649,0.0002866463,0.0005296561,0.000682393,0.0006356073,0.0009411855,0.0007336065,0.0008889959,0.0008498054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003678446,"about_ca_system_score_gemma":0.0007581139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002267816,"about_ca_topic_score_gemma":0.00407198,"domain_scores_codex":[0.9994247,0.0001551054,0.00002782484,0.0001920937,0.0001402343,0.0000599739],"domain_scores_gemma":[0.9991418,0.0003370375,0.00008618414,0.0002545377,0.000153513,0.00002678707],"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":[0.0002051379,0.0001844328,0.002099017,0.00008917752,0.00009856471,0.0001055243,0.00009216077,0.1284842,0.07237033,0.00676869,0.004182584,0.7853201],"study_design_scores_gemma":[0.000007524616,0.00005157347,0.001088361,0.000004789227,0.0000138481,0.00004715375,0.00002512553,0.9717157,0.01986215,0.005382434,0.001788161,0.00001319249],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02896171,0.0002122535,0.9683823,0.00006675648,0.00002742049,0.00002429534,0.0001156937,0.001465236,0.0007443876],"genre_scores_gemma":[0.5238842,0.0003751372,0.469278,0.0001536198,0.0000914295,0.0001182212,0.001887183,0.0003446849,0.003867514],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002267816,"threshold_uncertainty_score":0.00450927,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.093970308576222,"score_gpt":0.2031258955671578,"score_spread":0.1091555869909358,"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."}}