{"id":"W2403731734","doi":"10.21437/interspeech.2013-336","title":"Rapid and effective speaker adaptation of convolutional neural network based models for speech recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Speech recognition; TIMIT; Adaptation (eye); Convolutional neural network; Speaker recognition; Artificial neural network; Speaker diarisation; Hidden Markov model; Artificial intelligence; Pattern recognition (psychology)","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":[0.0002456901,0.00009441309,0.0001359504,0.00007203699,0.00006912028,0.00005508283,0.0001010136,0.00005280401,0.0002215411],"category_scores_gemma":[0.00005524324,0.00008348827,0.00006422809,0.0001436781,0.00004108041,0.0006574139,0.00002395629,0.00004036105,0.00002596665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001568145,"about_ca_system_score_gemma":0.00002507016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006045451,"about_ca_topic_score_gemma":0.00001154267,"domain_scores_codex":[0.9991934,0.0000814024,0.0001873304,0.0002319434,0.0001451651,0.0001607258],"domain_scores_gemma":[0.9988458,0.0005770521,0.00008454399,0.0001160088,0.0003151578,0.00006149113],"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":[0.00002047391,0.00003806062,0.00005014345,0.0000162918,0.0000142927,3.246496e-7,0.00004080854,0.001030329,0.0002209202,0.002427766,0.001137213,0.9950034],"study_design_scores_gemma":[0.0005707574,0.0001209477,0.00244034,0.00001817647,0.000008909882,0.000005841033,0.00002844688,0.956098,0.004403442,0.03610034,0.00009585349,0.0001089418],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05429549,0.00005073131,0.9421092,0.000459265,0.0001501249,0.0008140682,0.000009367346,0.00007026627,0.002041477],"genre_scores_gemma":[0.5754495,0.000006137598,0.4238463,0.0004125395,0.00006019131,0.0001496763,0.00001957396,0.000005607507,0.00005049589],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9948944,"threshold_uncertainty_score":0.3404553,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0454800610501761,"score_gpt":0.2299923264230991,"score_spread":0.184512265372923,"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."}}