{"id":"W4406369570","doi":"10.1121/10.0035093","title":"The AnySpeech Project —Open-vocabulary keyword spotting and phonetic transcription in any language","year":2024,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Keyword spotting; Vocabulary; Transcription (linguistics); Spotting; Computer science; Linguistics; Natural language processing; Artificial intelligence","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":[0.007897486,0.003788579,0.001951326,0.002312284,0.001769066,0.004400435,0.004601331,0.003009933,0.02162417],"category_scores_gemma":[0.01844168,0.001234074,0.002136051,0.001448846,0.001848386,0.008828889,0.009355859,0.004122543,0.0417054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001248775,"about_ca_system_score_gemma":0.004792987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01738036,"about_ca_topic_score_gemma":0.01559222,"domain_scores_codex":[0.9919826,0.002748509,0.0005604498,0.002164095,0.002067153,0.0004771641],"domain_scores_gemma":[0.9853958,0.004107795,0.000415811,0.004902236,0.003675569,0.001502697],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001516283,0.0006748181,0.002800308,0.001106488,0.0002796951,0.000403498,0.00142156,0.007354653,0.02445857,0.008291413,0.6109818,0.3407109],"study_design_scores_gemma":[0.001014879,0.001357692,0.00814038,0.0005480471,0.0003164623,0.001284418,0.003224956,0.2559809,0.07429786,0.0349923,0.6182867,0.0005553967],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03790981,0.002111835,0.5233502,0.004451755,0.005117397,0.001311697,0.133446,0.266127,0.0261743],"genre_scores_gemma":[0.08325773,0.0008428877,0.3670699,0.001647266,0.0006866697,0.002398364,0.4943556,0.02394097,0.02580058],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02162417,"threshold_uncertainty_score":0.07234007,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0107958205757932,"score_gpt":0.2845606125289348,"score_spread":0.2737647919531416,"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."}}