{"id":"W4411859426","doi":"10.1007/978-981-96-6599-0_22","title":"Optimizing Learnable Frequency-Domain Filterbanks for Depression Detection via Speech Representation Disentanglement","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Representation (politics); Speech recognition; Frequency domain; Domain (mathematical analysis); Algorithm; Artificial intelligence; Mathematics; Computer vision","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008377624,0.0004639702,0.0004703626,0.0009819551,0.000484267,0.0005955488,0.001697231,0.0003171182,0.00005748768],"category_scores_gemma":[0.0001641934,0.0004475374,0.0002321978,0.0006167176,0.0002014378,0.0007273222,0.0006803441,0.0004777107,0.00002123505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005222384,"about_ca_system_score_gemma":0.0002588058,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005758865,"about_ca_topic_score_gemma":0.0001739907,"domain_scores_codex":[0.9962119,0.00006234054,0.0006212689,0.001668335,0.0008333792,0.0006027827],"domain_scores_gemma":[0.9974229,0.0006645954,0.0003494112,0.001113069,0.0003079639,0.0001420053],"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":[0.00001362559,0.00002921756,0.00003549092,0.00004916151,0.00001571964,0.00003442039,0.000247851,0.001119668,0.002935893,0.001344649,0.00003434602,0.99414],"study_design_scores_gemma":[0.0007045429,0.000186423,0.00006438825,0.0007662461,0.00002899541,0.00008263534,0.000001621235,0.4724631,0.118183,0.4052844,0.001368782,0.0008658443],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000796561,0.0002384241,0.9895723,0.0004982604,0.002026857,0.0009712015,0.00001027847,0.0002035039,0.006399496],"genre_scores_gemma":[0.01681894,0.00004010783,0.9811631,0.0007443951,0.0003387359,0.0000845126,0.00001921864,0.00002962976,0.0007612886],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9932741,"threshold_uncertainty_score":0.9997976,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02133187621396906,"score_gpt":0.2667836558084923,"score_spread":0.2454517795945233,"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."}}