{"id":"W4414995823","doi":"10.21203/rs.3.rs-7808032/v1","title":"Mixed Signal Design Using C++ and DSP Acceleration for Low Latency and Secure Speech Systems","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Latency (audio); Digital signal processing; Low latency (capital markets); Voice activity detection; Novelty; Speech processing; Signal processing; Digital signal processor","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":[0.0004621545,0.0009057511,0.0003231671,0.0006648515,0.0004812078,0.001319204,0.00113768,0.0005604663,0.01620615],"category_scores_gemma":[0.001058671,0.0003459204,0.0003078604,0.0003605888,0.0002022673,0.0005521788,0.0003775709,0.0006423395,0.003819868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005338187,"about_ca_system_score_gemma":0.0007545195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001301379,"about_ca_topic_score_gemma":0.002786384,"domain_scores_codex":[0.9995072,0.0000938087,0.00004050361,0.00006977224,0.0002205019,0.00006816514],"domain_scores_gemma":[0.9993328,0.0001768752,0.00005738586,0.00007507067,0.0003278395,0.00002995234],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001585962,0.0002629951,0.000777483,0.0005465958,0.0001396629,0.0002868097,0.0001846793,0.04427582,0.3575991,0.01733444,0.008180814,0.5688256],"study_design_scores_gemma":[0.0002777279,0.002327692,0.000941371,0.0000928099,0.0001516395,0.0005473307,0.0000775285,0.5851333,0.3581214,0.005288013,0.04698088,0.00006041877],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01974878,0.0003079071,0.9662138,0.0001347502,0.0001291475,0.000189128,0.00008433664,0.004628021,0.008564188],"genre_scores_gemma":[0.4287445,0.0002359685,0.551228,0.0002747432,0.0001184758,0.0002969592,0.0002721252,0.0007067516,0.01812234],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01620615,"threshold_uncertainty_score":0.05421495,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2481162879091529,"score_gpt":0.3979784810351982,"score_spread":0.1498621931260454,"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."}}