{"id":"W4401994215","doi":"10.3390/acoustics6030042","title":"Text-Independent Phone-to-Audio Alignment Leveraging SSL (TIPAA-SSL) Pre-Trained Model Latent Representation and Knowledge Transfer","year":2024,"lang":"en","type":"article","venue":"Acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Phone; Speech recognition; Artificial intelligence; Classifier (UML); TIMIT; Transfer of learning; Hidden Markov model; Natural language processing; Frame (networking); Representation (politics)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003208311,0.0002022004,0.000190525,0.0001946029,0.0001224238,0.000435904,0.000320913,0.00008550363,0.00004533501],"category_scores_gemma":[0.00004826547,0.0001886839,0.000084811,0.0003330047,0.00002797643,0.0002949557,0.0001514065,0.000152291,0.0001613573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001151495,"about_ca_system_score_gemma":0.0001085895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001643551,"about_ca_topic_score_gemma":0.000007898407,"domain_scores_codex":[0.9983361,0.00005682633,0.0003044773,0.0006054826,0.0003757585,0.0003212939],"domain_scores_gemma":[0.9991727,0.0001715528,0.0000189706,0.0003494644,0.00008865283,0.0001986341],"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":[0.00005613998,0.0004286623,0.0001598108,0.0003305067,0.0002962502,0.0002931299,0.02589255,0.03080411,0.1592186,0.008812982,0.0140192,0.7596881],"study_design_scores_gemma":[0.0003008106,0.00004097913,0.0009534511,0.0001080955,0.00006123319,0.00005253404,0.0001369236,0.9795519,0.01553405,0.00241759,0.0005667915,0.0002756387],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.114272,0.0002405761,0.8818075,0.0009618955,0.0006085535,0.000291374,0.00001507979,0.000288957,0.001514004],"genre_scores_gemma":[0.9669216,0.0001383156,0.03034897,0.0003673561,0.0001043433,0.0000496929,0.000005805248,0.00002471532,0.002039223],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9487478,"threshold_uncertainty_score":0.7694308,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03828787458081839,"score_gpt":0.286544157521967,"score_spread":0.2482562829411487,"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."}}