{"meta":{"query_hash":"50a8d0646b88","filters":{"venue":"Interspeech 2022"},"cohort_total":3,"direct_labels_cover":0,"predictions_cover":3,"exported":3,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/50a8d0646b88","api":"https://metacan.xera.ac/api/v1/cohort?venue=Interspeech+2022"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; End-to-end principle; Computer network","score_opus":0.02692692012041936,"score_gpt":0.27559052982646537,"score_spread":0.248663609706046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297841482","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061559536,0.0020336756,0.9123696,0.0006290958,0.00025122042,0.00015481403,0.0006523278,0.014413146,0.007936485],"genre_scores_gemma":[0.6684049,0.0007289307,0.31107658,0.00059197925,0.00008003786,0.00022177109,0.0018475682,0.0003586963,0.0166896],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99970955,0.00004635135,0.000019825047,0.00008316289,0.000108256936,0.000032891134],"domain_scores_gemma":[0.9997552,0.000080384525,0.00002065056,0.000045245764,0.00008631579,0.000012218306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045603956,0.0006837757,0.00033060438,0.00034706082,0.0002692783,0.0006331495,0.0010607733,0.00077955436,0.008531108],"category_scores_gemma":[0.0012337709,0.00020595477,0.00022966869,0.00037661777,0.00034682298,0.0016473087,0.00082145596,0.0012057463,0.002697292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005370138,0.00018196506,0.00056396367,0.0002196752,0.000051620034,0.00017577202,0.00016572216,0.070016235,0.08528774,0.007320559,0.012796641,0.8226831],"study_design_scores_gemma":[0.000032138687,0.00018610888,0.00045587175,0.000033381708,0.000025934061,0.00010166279,0.000070407266,0.93076336,0.05141743,0.008600439,0.008285872,0.000027423559],"about_ca_topic_score_codex":0.005031242,"about_ca_topic_score_gemma":0.011058245,"teacher_disagreement_score":0.008531108,"about_ca_system_score_codex":0.00055050774,"about_ca_system_score_gemma":0.0008983724,"threshold_uncertainty_score":0.02853936},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.01880117531733043,"score_gpt":0.23215500689416602,"score_spread":0.21335383157683557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297841830","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032687325,0.00084785634,0.94683695,0.00041248047,0.00031267598,0.00010335286,0.000885305,0.014091294,0.0038228624],"genre_scores_gemma":[0.65066046,0.0005174534,0.3298153,0.0006997507,0.00012090232,0.00027853993,0.0036678123,0.00087158487,0.013368097],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997147,0.000054663822,0.000013284195,0.00014091015,0.00004734483,0.000029234583],"domain_scores_gemma":[0.9996916,0.00014737976,0.000018599349,0.00006208089,0.000054376957,0.000025974956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005575834,0.0013087116,0.0006085241,0.00047878874,0.00036777515,0.00082684326,0.0018330675,0.0012737396,0.004003125],"category_scores_gemma":[0.0014477583,0.00044127018,0.00080799044,0.0006124548,0.00053251424,0.0018552117,0.0013273818,0.0019166014,0.0022837417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006628533,0.00026382066,0.001635847,0.00021191005,0.0001702461,0.00035158294,0.00023438147,0.36231568,0.031568654,0.010815186,0.017607896,0.57416195],"study_design_scores_gemma":[0.000037862654,0.00007184809,0.00024918863,0.000010029801,0.000022721068,0.00004821633,0.000026713913,0.9771527,0.006528786,0.012764061,0.0030676255,0.00002020129],"about_ca_topic_score_codex":0.006591864,"about_ca_topic_score_gemma":0.013655712,"teacher_disagreement_score":0.006591864,"about_ca_system_score_codex":0.000533464,"about_ca_system_score_gemma":0.0011097239,"threshold_uncertainty_score":0.013391852},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ubisoft (Canada)","funders":"","keywords":"Prosody; Computer science; Speech synthesis; Speech recognition; Transfer (computing); Natural language processing","score_opus":0.02503636111819494,"score_gpt":0.28065545976882816,"score_spread":0.2556190986506332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297841867","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024709249,0.00064914476,0.95603156,0.00023266161,0.00040490704,0.00019043658,0.0005085266,0.011439923,0.0058336034],"genre_scores_gemma":[0.58360815,0.0006115011,0.3837751,0.0006375303,0.00021228183,0.0006794605,0.0029538579,0.0022014545,0.025320698],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996499,0.000084128056,0.000017234514,0.00012227843,0.00009508589,0.000031317442],"domain_scores_gemma":[0.99960154,0.0002002753,0.000019107805,0.00009710409,0.00005237169,0.000029614679],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009278741,0.0012333755,0.0005582059,0.0002489874,0.00026664813,0.0006383726,0.0014814776,0.0009852932,0.008162303],"category_scores_gemma":[0.0020341442,0.0003246837,0.0009129012,0.00012273437,0.00046285897,0.0010680243,0.0021104298,0.0019495432,0.0034247919],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061505876,0.00029496028,0.00065917685,0.00036686074,0.00022390978,0.00058833475,0.000287843,0.39550757,0.095704265,0.008225786,0.012054127,0.48547214],"study_design_scores_gemma":[0.000045451543,0.0002125647,0.00018292009,0.000022938844,0.00002784206,0.000199974,0.000022532138,0.96399486,0.024137747,0.0049718497,0.0061545568,0.000026668056],"about_ca_topic_score_codex":0.000951498,"about_ca_topic_score_gemma":0.0014312977,"teacher_disagreement_score":0.008162303,"about_ca_system_score_codex":0.00029775058,"about_ca_system_score_gemma":0.0004375832,"threshold_uncertainty_score":0.027305603},"labels":[],"label_agreement":null}]}