{"id":"W2128251029","doi":"10.1109/icassp.2009.4960505","title":"Combining frontend-based memory with MFCC features for Bandwidth Extension of narrowband speech","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Data Compression Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Mel-frequency cepstrum; Narrowband; Speech recognition; Bandwidth (computing); Correlation; Bandwidth extension; Artificial intelligence; Feature (linguistics); Distortion (music); Encoding (memory); Pattern recognition (psychology); Feature extraction; Speech coding; Mathematics; Telecommunications; Audio signal","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020175,0.0001682906,0.0002677434,0.000127508,0.00009727829,0.000043023,0.0007117834,0.00006260574,0.00001167717],"category_scores_gemma":[0.00005147391,0.0001161664,0.00005622102,0.00019429,0.00004907186,0.0004622031,0.0000816099,0.000107817,9.706159e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001758312,"about_ca_system_score_gemma":0.00005242562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001310709,"about_ca_topic_score_gemma":0.000007114338,"domain_scores_codex":[0.9987945,0.00003118063,0.0002223571,0.0004298734,0.000287752,0.0002343595],"domain_scores_gemma":[0.9985621,0.0001493912,0.0001535189,0.0008574508,0.0002010399,0.00007649491],"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":[0.0007662027,0.0006373401,0.0002095854,0.00008969771,0.00002977431,0.0000610609,0.0003676169,0.001333872,0.2184353,0.03742764,0.08415594,0.656486],"study_design_scores_gemma":[0.001481407,0.001182296,0.001538043,0.0002078435,0.000008338962,0.00002505478,0.00003097264,0.02330442,0.9603771,0.01009812,0.001456497,0.0002899252],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003095109,0.0001498971,0.9934053,0.000767671,0.00006631393,0.0003818642,0.000006793947,0.0004235792,0.001703446],"genre_scores_gemma":[0.3812349,0.00000282402,0.617719,0.0007471067,0.00001248028,0.00001025895,0.000009284681,0.000007161359,0.00025701],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7419418,"threshold_uncertainty_score":0.4737128,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01450693336839389,"score_gpt":0.2696574415225063,"score_spread":0.2551505081541124,"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."}}