{"id":"W4319862706","doi":"10.1109/slt54892.2023.10022986","title":"Flow-ER: A Flow-Based Embedding Regularization Strategy for Robust Speech Representation Learning","year":2023,"lang":"en","type":"article","venue":"2022 IEEE Spoken Language Technology Workshop (SLT)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Embedding; Computer science; Regularization (linguistics); Artificial intelligence; Machine learning; Deep learning; Speech recognition; Representation (politics); Feature learning; Bottleneck; Task (project management)","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000788839,0.0003021235,0.0003758432,0.001318707,0.000431137,0.0002243682,0.0009338796,0.0004801187,0.0002442375],"category_scores_gemma":[0.0009493889,0.0003250471,0.000186611,0.003824598,0.0001034982,0.0003821765,0.0001719142,0.0005407744,0.0002532136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001220371,"about_ca_system_score_gemma":0.00009946498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001153628,"about_ca_topic_score_gemma":0.00005518499,"domain_scores_codex":[0.9974028,0.0001401072,0.0004623836,0.0009251652,0.0004022735,0.0006672532],"domain_scores_gemma":[0.9982321,0.000384481,0.0002301545,0.0008912784,0.0001680041,0.00009395161],"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":[0.00004658244,0.00008159614,0.0003239154,0.00005193235,0.00008116487,0.000355288,0.0007726929,0.1404864,0.01298351,0.001337923,0.005775098,0.8377039],"study_design_scores_gemma":[0.0007272897,0.00007228027,0.000088284,0.00007656162,0.00003181634,0.0000363229,0.002747749,0.9545882,0.03904675,0.001639302,0.0005752031,0.0003702395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08357388,0.0001486366,0.906819,0.002765215,0.000731878,0.0008052749,0.00001964641,0.004271099,0.0008653363],"genre_scores_gemma":[0.4059957,0.00007892247,0.580592,0.0004460055,0.0004335803,0.0007223342,0.000610472,0.000148894,0.01097208],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8373337,"threshold_uncertainty_score":0.9999201,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03353607308453113,"score_gpt":0.30544206453765,"score_spread":0.2719059914531189,"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."}}