{"id":"W4285182272","doi":"10.18653/v1/2022.acl-long.507","title":"Requirements and Motivations of Low-Resource Speech Synthesis for Language Revitalization","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Edinburgh; UK Research and Innovation","keywords":"Naturalness; Computer science; Speech synthesis; Speech technology; Field (mathematics); Resource (disambiguation); Natural language processing; Indigenous; Artificial intelligence; Speech recognition","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006722916,0.0008219084,0.0008088949,0.0006087764,0.001000299,0.002553062,0.002307608,0.001548092,0.00402193],"category_scores_gemma":[0.01371542,0.0006666639,0.0004834256,0.0004885622,0.002241956,0.004444027,0.002956015,0.002895289,0.002642525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00133686,"about_ca_system_score_gemma":0.002460149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003820865,"about_ca_topic_score_gemma":0.002769559,"domain_scores_codex":[0.9967695,0.001359247,0.0002070829,0.00064964,0.0007253194,0.000289116],"domain_scores_gemma":[0.9823829,0.01043901,0.0006256711,0.002186932,0.003633926,0.0007315687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.001958206,0.000720873,0.006732242,0.00229373,0.00008013443,0.00160696,0.00658735,0.07950918,0.3139031,0.1454551,0.00569699,0.4354562],"study_design_scores_gemma":[0.0002757124,0.001891833,0.00734536,0.0005246767,0.0001287066,0.002141968,0.007188396,0.4644299,0.2417959,0.1189811,0.1550156,0.0002807762],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2437074,0.00260499,0.7008902,0.01315118,0.000196015,0.0006928747,0.0006409205,0.003340896,0.03477552],"genre_scores_gemma":[0.7221824,0.001082717,0.2656021,0.000724689,0.0001683087,0.0007387871,0.0008934202,0.0007408724,0.007866682],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006722916,"threshold_uncertainty_score":0.03555459,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008099032325082663,"score_gpt":0.2482365390038449,"score_spread":0.2401375066787623,"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."}}