{"id":"W4410431605","doi":"10.1016/j.csl.2025.101815","title":"BERSting at the screams: A benchmark for distanced, emotional and shouted speech recognition","year":2025,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Benchmark (surveying); Speech recognition; Emotion recognition; Natural language processing","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.000510506,0.00022818,0.0002382663,0.0001658172,0.0004537936,0.0003452665,0.0005801067,0.00009631646,0.0001782477],"category_scores_gemma":[0.000129941,0.0001806578,0.0001386981,0.0004478738,0.00009888331,0.000306313,0.0004410895,0.000151844,0.00003746249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008015053,"about_ca_system_score_gemma":0.00005270909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000355907,"about_ca_topic_score_gemma":0.0001359585,"domain_scores_codex":[0.9983684,0.0001030567,0.0003176718,0.0005967999,0.0002573907,0.000356707],"domain_scores_gemma":[0.9985308,0.0006088314,0.0001144772,0.0004994519,0.0001552068,0.00009120351],"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":[0.00002017726,0.00004764696,0.000134582,0.00004149218,0.00004818597,0.00003242083,0.0004761997,0.000001514132,0.0004442186,0.001517634,0.009197186,0.9880387],"study_design_scores_gemma":[0.01134495,0.0007578636,0.03909645,0.002437375,0.0004647987,0.001965131,0.00255356,0.5765508,0.164855,0.05076406,0.1451205,0.004089538],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1277205,0.0006203275,0.8544229,0.003812687,0.001003271,0.0008481196,0.000112748,0.0003473195,0.0111121],"genre_scores_gemma":[0.07464375,0.00004823851,0.914466,0.005409071,0.000693904,0.0001318319,0.0002395434,0.00003380184,0.004333893],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9839492,"threshold_uncertainty_score":0.736701,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01565752871258395,"score_gpt":0.2604487816432463,"score_spread":0.2447912529306624,"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."}}