{"id":"W4384828046","doi":"10.1057/s41599-023-01931-4","title":"Using a forced aligner for prosody research","year":2023,"lang":"en","type":"article","venue":"Humanities and Social Sciences Communications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Georgia Institute of Technology","keywords":"Computer science; Prosody; Mandarin Chinese; Syllable; Phrase; Natural language processing; Speech recognition; Sentence; Annotation; Artificial intelligence; Linguistics","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.001481018,0.00005239392,0.00008217476,0.0002067135,0.00548907,0.0005440883,0.001199887,0.000033667,0.000009918773],"category_scores_gemma":[0.00007461272,0.00004838618,0.00004075787,0.0006708681,0.0009466236,0.0003449094,0.0005751284,0.00007256249,0.0000132273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002475241,"about_ca_system_score_gemma":0.00008392829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001070348,"about_ca_topic_score_gemma":0.0001758086,"domain_scores_codex":[0.9990258,0.0001653853,0.0001240964,0.0001706545,0.0002413302,0.0002727621],"domain_scores_gemma":[0.9988559,0.0006141769,0.00003702888,0.0003020899,0.0001731116,0.0000176739],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[6.34266e-7,0.00001494223,0.00002612288,0.000007525402,0.000004351437,1.552135e-7,0.008205771,6.624596e-7,0.0003425716,0.975839,0.001920471,0.01363784],"study_design_scores_gemma":[0.0004603065,0.0001806206,0.001515605,0.00005298436,0.00001510462,0.000007767115,0.03495283,0.2567735,0.000505434,0.3623117,0.3427409,0.0004832868],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3330918,0.001460389,0.1194996,0.1004266,0.001101947,0.00497494,0.0001594864,0.002622875,0.4366624],"genre_scores_gemma":[0.8970551,0.0002911694,0.09843238,0.00100791,0.0001438232,0.0003508291,0.00001434743,0.00001201409,0.002692387],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6135272,"threshold_uncertainty_score":0.9958056,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7762389046443241,"score_gpt":0.5030580593464857,"score_spread":0.2731808452978384,"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."}}