{"id":"W3207572704","doi":"10.1109/icassp43922.2022.9746260","title":"Continual Learning Using Lattice-Free MMI for Speech Recognition","year":2022,"lang":"en","type":"article","venue":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"NeuroRx Research (Canada)","funders":"","keywords":"Forgetting; Computer science; Regularization (linguistics); Artificial neural network; Exploit; Speech recognition; Word error rate; Artificial intelligence; Acoustic model; Domain adaptation; Machine learning; Speech processing","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001768927,0.0008779102,0.0008221137,0.0005783949,0.000390153,0.0006681624,0.001800479,0.0009534013,0.001883883],"category_scores_gemma":[0.005306642,0.0004816729,0.0007014832,0.0005636167,0.001040683,0.001844299,0.001630142,0.002155064,0.000876258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000669204,"about_ca_system_score_gemma":0.0007509102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002790275,"about_ca_topic_score_gemma":0.004549101,"domain_scores_codex":[0.9993862,0.0001924112,0.00003759883,0.0001792061,0.0001449114,0.00005964966],"domain_scores_gemma":[0.9979894,0.001016531,0.0001818976,0.0004093348,0.0003037141,0.00009913377],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002356696,0.0002743464,0.002122537,0.0001014548,0.00008630584,0.0001008058,0.0001431922,0.6508461,0.01377835,0.00847843,0.001814178,0.3220185],"study_design_scores_gemma":[0.000004944629,0.00003566804,0.00008122279,0.00000248235,0.000002628423,0.00001402492,0.000005573804,0.9962955,0.001788073,0.001592091,0.0001731367,0.000004641763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05110329,0.0004293164,0.944818,0.0001897132,0.00005396259,0.0000450421,0.00006565566,0.001948861,0.001346208],"genre_scores_gemma":[0.7162337,0.0001834114,0.2804162,0.0001867939,0.00005599415,0.0001407574,0.0003006149,0.0002084708,0.002274],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002790275,"threshold_uncertainty_score":0.009355128,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09276504634484213,"score_gpt":0.3157352333647936,"score_spread":0.2229701870199515,"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."}}