{"id":"W2887814324","doi":"10.1109/slt.2018.8639585","title":"Speaker Recognition from Raw Waveform with SincNet","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Compute Canada","keywords":"Computer science; Sinc function; Waveform; Convolutional neural network; Speech recognition; Speaker recognition; Filter (signal processing); Formant; Artificial intelligence; Pattern recognition (psychology); Convolution (computer science); Artificial neural network; Telecommunications; Computer vision","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","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002167013,0.0003346728,0.0003393298,0.0001659835,0.00009168003,0.0004942781,0.0009383648,0.0003016651,0.004048522],"category_scores_gemma":[0.00004059442,0.0002458821,0.000128451,0.0001667126,0.00008511487,0.0003151593,0.0007873478,0.0003352264,0.003838398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000799242,"about_ca_system_score_gemma":0.0001526507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004383115,"about_ca_topic_score_gemma":0.0002845378,"domain_scores_codex":[0.9979482,0.00007669192,0.0003155225,0.0009078092,0.0004505235,0.0003011956],"domain_scores_gemma":[0.9981493,0.0001246169,0.0002008551,0.001088744,0.0002771473,0.0001592824],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005523198,0.0002042236,0.000174362,0.00003934959,0.0002457302,0.00009032014,0.0004996991,0.000003406095,0.0001268587,0.000495645,0.02172943,0.9763358],"study_design_scores_gemma":[0.00344464,0.0008187801,0.01487567,0.002376836,0.0003844658,0.0002555307,0.0003390158,0.1403251,0.263363,0.5071959,0.0605454,0.00607565],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03824553,0.0000343211,0.7197115,0.001429284,0.00141112,0.0004644992,0.00005979059,0.0008149996,0.2378289],"genre_scores_gemma":[0.1145344,0.00009229768,0.8778856,0.002840531,0.001109452,0.00009689527,0.0005167275,0.00005546068,0.002868694],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9702601,"threshold_uncertainty_score":0.9999993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0396549809171314,"score_gpt":0.2325995190391958,"score_spread":0.1929445381220644,"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."}}