{"id":"W2900161882","doi":"10.1109/icassp.2019.8682611","title":"Adapting End-to-end Neural Speaker Verification to New Languages and Recording Conditions with Adversarial Training","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal; McGill University","funders":"","keywords":"Adversarial system; Computer science; NIST; Speaker verification; Speech recognition; Task (project management); Artificial neural network; Speaker recognition; Embedding; End-to-end principle; Margin (machine learning); Artificial intelligence; Training (meteorology); Speaker diarisation; Residual; Combing; Machine learning; Algorithm; Engineering","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":[0.00202935,0.001093712,0.0006988432,0.000270897,0.0002936401,0.0006242608,0.00159079,0.001161403,0.002163851],"category_scores_gemma":[0.005198215,0.0004391864,0.0006523625,0.0001891115,0.0009453673,0.001596825,0.002289154,0.00238979,0.001695304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005394362,"about_ca_system_score_gemma":0.0005722408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001857504,"about_ca_topic_score_gemma":0.002304246,"domain_scores_codex":[0.9988902,0.000386218,0.00004234086,0.0003311854,0.0002332037,0.000116828],"domain_scores_gemma":[0.9985241,0.0007092039,0.0001094772,0.0003918625,0.0002119562,0.0000533286],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004112548,0.0001742891,0.001466933,0.00007878146,0.0001240688,0.0001818672,0.0001160787,0.7674162,0.03564277,0.004925389,0.002489148,0.1869732],"study_design_scores_gemma":[0.000003888397,0.00003686683,0.0001545319,0.000004574674,0.000006322992,0.00004587775,0.000006910194,0.9900593,0.007336458,0.001998235,0.0003387885,0.000008233659],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03984424,0.0002256926,0.9555407,0.0001901875,0.0001055112,0.00005906079,0.00009509134,0.002076718,0.001862731],"genre_scores_gemma":[0.8236669,0.0001609386,0.168513,0.0003364596,0.00006431923,0.0001016461,0.0004295413,0.0002421708,0.006485205],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002163851,"threshold_uncertainty_score":0.01073235,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05388103435155326,"score_gpt":0.2965635239524541,"score_spread":0.2426824896009008,"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."}}