{"id":"W7160921222","doi":"10.1121/10.0041466","title":"A Praat script for unsupervised phoneme segmentation based on spectro-temporal representation","year":2025,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"TIMIT; Segmentation; Representation (politics); Spectrogram; Set (abstract data type); Measure (data warehouse); Software; Boundary (topology); Data set","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":[0.0006249677,0.00009359535,0.0002016206,0.00003824935,0.0001808441,0.0000424788,0.0007027672,0.00003796078,0.00002956501],"category_scores_gemma":[0.000328831,0.00005203771,0.0003891385,0.0004586172,0.0001610787,0.0001262952,0.00006626738,0.0001662883,0.000002225311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008208423,"about_ca_system_score_gemma":0.0001381936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002118199,"about_ca_topic_score_gemma":4.176833e-7,"domain_scores_codex":[0.9987657,0.0001985742,0.0003642511,0.0001063898,0.0004194101,0.0001456771],"domain_scores_gemma":[0.9981047,0.0009672332,0.0003502214,0.0003117291,0.0002251005,0.000040998],"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":[0.001343713,0.001211651,0.0006833595,0.0002049758,0.0006229713,0.00000225658,0.002605745,0.01445237,0.2035928,0.0003993945,0.2848324,0.4900483],"study_design_scores_gemma":[0.0009715883,0.0002906118,0.0008676637,0.00009917514,0.000133942,0.000006132375,0.001079679,0.9416779,0.05007964,0.00371898,0.0009975919,0.00007706574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002832256,0.0000314901,0.9736547,0.02265344,0.0003005402,0.0002435685,0.000004330031,0.00001387012,0.000265759],"genre_scores_gemma":[0.344446,0.00006188092,0.6460837,0.009124116,0.00009927084,0.000007305163,0.000001166973,0.000007583444,0.0001690064],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9272256,"threshold_uncertainty_score":0.2122036,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02254720725293952,"score_gpt":0.2854492572117903,"score_spread":0.2629020499588508,"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."}}