{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008220381,0.001310867,0.0009304295,0.0009020194,0.0005581498,0.00106928,0.001849334,0.001242671,0.006201812],"category_scores_gemma":[0.00302218,0.0004242694,0.0009758798,0.0009864997,0.0005772815,0.002627116,0.002057495,0.00232158,0.01003675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005373092,"about_ca_system_score_gemma":0.001317735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004336107,"about_ca_topic_score_gemma":0.009221765,"domain_scores_codex":[0.9989998,0.0001832704,0.00005365143,0.0004225351,0.0002366826,0.0001040931],"domain_scores_gemma":[0.9987972,0.0002677854,0.000097786,0.0004434669,0.0003182867,0.00007551945],"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":[0.0003608555,0.0003916194,0.001467164,0.0001829901,0.0001229532,0.0002110656,0.0001493556,0.04761332,0.04869106,0.003862574,0.02155696,0.8753901],"study_design_scores_gemma":[0.00003281519,0.0001717345,0.001115594,0.00002470608,0.00004298003,0.0002086916,0.00007148669,0.9435526,0.03867345,0.007116787,0.008943954,0.00004513367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02240747,0.0006792842,0.9533252,0.0002761475,0.0003723903,0.0001270554,0.001126687,0.0175924,0.004093422],"genre_scores_gemma":[0.5002521,0.0005255689,0.4592279,0.0008319007,0.0004752622,0.0004513058,0.01016955,0.001609118,0.02645735],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006201812,"threshold_uncertainty_score":0.02074713,"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."}}