{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":3,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":3,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"50a8d0646b88","filters":{"venue":"Interspeech 2022"}},"results":[{"id":"W4297841867","doi":"10.21437/interspeech.2022-10761","title":"Daft-Exprt: Cross-Speaker Prosody Transfer on Any Text for Expressive Speech Synthesis","year":2022,"lang":"en","type":"article","venue":"Interspeech 2022","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ubisoft (Canada)","funders":"","keywords":"Prosody; Computer science; Speech synthesis; Speech recognition; Transfer (computing); Natural language processing","authors":[{"name":"Julian Zaïdi","is_ca":true},{"name":"Hugo Seuté","is_ca":true},{"name":"Benjamin van Niekerk","is_ca":false},{"name":"Marc-André Carbonneau","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02503636111819494,"gpt":0.2806554597688282,"spread":0.2556190986506332,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008573191,0.0003929927,0.0004294277,0.0004246211,0.0006859229,0.0004187241,0.002049583,0.0001042277,0.005776633],"category_scores_gemma":[0.0003410321,0.0003905981,0.0004714908,0.0006280034,0.000108084,0.0004684788,0.0004892619,0.0004905102,0.0003491863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003428696,"about_ca_system_score_gemma":0.0001254577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002306814,"about_ca_topic_score_gemma":0.000007449617,"domain_scores_codex":[0.9963897,0.0002781676,0.0005293026,0.001169008,0.0009239573,0.0007099057],"domain_scores_gemma":[0.9974507,0.0009381259,0.0001158643,0.001082437,0.0002064688,0.0002064206],"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":[0.001265865,0.002646917,0.0003986921,0.0001432506,0.000507167,0.0008311617,0.007060428,0.000175772,0.06669888,0.02606915,0.1162676,0.7779351],"study_design_scores_gemma":[0.001826317,0.001090686,0.0005410649,0.0001085789,0.00005752286,0.0003311233,0.002407758,0.006869832,0.7281638,0.003855851,0.2534267,0.001320777],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5953729,0.0004750758,0.2971759,0.01531893,0.007928592,0.00591102,0.001752002,0.002293437,0.07377215],"genre_scores_gemma":[0.9598255,0.00001987254,0.02409899,0.003436728,0.0002958142,0.003195804,0.00003248989,0.0001061262,0.008988721],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7766144,"threshold_uncertainty_score":0.9998546,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4297841830","doi":"10.21437/interspeech.2022-11066","title":"SoundChoice: Grapheme-to-Phoneme Models with Semantic Disambiguation","year":2022,"lang":"en","type":"article","venue":"Interspeech 2022","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University; Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Grapheme; Computer science; Natural language processing; Artificial intelligence","authors":[{"name":"Artem Ploujnikov","is_ca":true},{"name":"Mirco Ravanelli","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01880117531733043,"gpt":0.232155006894166,"spread":0.2133538315768356,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003844465,0.0001726359,0.0001769186,0.0003567721,0.0003601504,0.0001801178,0.001038163,0.00002423078,0.001244545],"category_scores_gemma":[0.00003214419,0.000165218,0.00009836292,0.001119075,0.00003012318,0.0004259238,0.000501667,0.000242871,0.0001896384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001750902,"about_ca_system_score_gemma":0.00006554546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001104968,"about_ca_topic_score_gemma":0.00007115402,"domain_scores_codex":[0.9980057,0.0001385326,0.0002286568,0.0005497168,0.0007539185,0.0003234676],"domain_scores_gemma":[0.9989725,0.00009459046,0.0000883977,0.0006099125,0.0000988285,0.0001357826],"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":[0.0004918166,0.001970065,0.001109111,0.00008226929,0.0005698011,0.0007567065,0.0261226,0.009879524,0.02286215,0.1312202,0.1258645,0.6790712],"study_design_scores_gemma":[0.004395087,0.00321892,0.001925785,0.0001894835,0.0001523716,0.00144576,0.013965,0.674513,0.03725662,0.1501738,0.1091039,0.003660271],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1108626,0.00006651214,0.8707237,0.007036894,0.0007619806,0.0005013937,0.00001942812,0.0004821345,0.009545295],"genre_scores_gemma":[0.9490138,0.000006216032,0.04511077,0.003374516,0.00005219699,0.0003047211,0.00001413121,0.00002900288,0.002094601],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8381512,"threshold_uncertainty_score":0.9996685,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4297841482","doi":"10.21437/interspeech.2022-760","title":"Low-bit Shift Network for End-to-End Spoken Language Understanding","year":2022,"lang":"en","type":"article","venue":"Interspeech 2022","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; End-to-end principle; Computer network","authors":[{"name":"Anderson R. Avila","is_ca":true},{"name":"Khalil Bibi","is_ca":true},{"name":"Rui Heng Yang","is_ca":true},{"name":"Xinlin Li","is_ca":true},{"name":"Chao Xing","is_ca":true},{"name":"Xiao Dong Chen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02692692012041936,"gpt":0.2755905298264654,"spread":0.248663609706046,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003609229,0.0001311214,0.0001436079,0.00008585459,0.0004836189,0.0001463637,0.001078671,0.00002270446,0.0005839712],"category_scores_gemma":[0.0000140349,0.0001386958,0.0001137404,0.000671914,0.00002135171,0.0001335258,0.0008775043,0.0002352544,0.00003407489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002529813,"about_ca_system_score_gemma":0.00003832141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003693823,"about_ca_topic_score_gemma":0.00005463499,"domain_scores_codex":[0.9986075,0.00004990969,0.0001985871,0.0004557281,0.0002728263,0.0004154593],"domain_scores_gemma":[0.9990934,0.0002480386,0.00007144469,0.0004578832,0.00001598035,0.0001132903],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008267831,0.0001973445,0.0001938645,0.00002373661,0.00008599097,0.00009687681,0.006110519,0.01203262,0.002449861,0.5857924,0.3438093,0.04912483],"study_design_scores_gemma":[0.002823927,0.001867137,0.0006461161,0.0001990894,0.00009099892,0.0001804458,0.0136275,0.1729693,0.006685094,0.1532959,0.6451306,0.002483759],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02339223,0.0001889222,0.9625043,0.009541193,0.001142835,0.0007090361,0.00007411413,0.0002563653,0.002190975],"genre_scores_gemma":[0.9864455,0.000003185327,0.008683696,0.002598348,0.0003551195,0.0003524583,0.00002927402,0.0000216997,0.001510673],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9630533,"threshold_uncertainty_score":0.6394075,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}