{"id":"W2988294997","doi":"10.1109/tim.2006.887773","title":"Speech Quality Evaluation: A New Application of Digital Watermarking","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Instrumentation and Measurement","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Speech recognition; Digital watermarking; Speech coding; Linear predictive coding; PSQM; PESQ; Speech processing; Quality (philosophy); Mean opinion score; Watermark; Quantization (signal processing); Voice activity detection; Intelligibility (philosophy); Artificial intelligence; Speech enhancement; Computer vision; Noise reduction; Embedding; Engineering","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":[0.001106443,0.0001059468,0.0001036837,0.0001804636,0.0001207396,0.00006091483,0.0001412303,0.00004121544,0.000004845999],"category_scores_gemma":[0.00000384758,0.0001008595,0.0000541302,0.0002442881,0.00003388209,0.0004879581,0.000002065345,0.00007547873,0.000002125131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001015763,"about_ca_system_score_gemma":0.00004570278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003374003,"about_ca_topic_score_gemma":0.00003071804,"domain_scores_codex":[0.998523,0.00003967388,0.0003551336,0.0002365458,0.0007105367,0.0001351014],"domain_scores_gemma":[0.9993501,0.00002371763,0.0001359988,0.0002332298,0.0001792633,0.00007767193],"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":[0.00003829254,0.00008044267,0.0003398813,0.00001445691,0.0000179727,2.368628e-7,0.0004092615,0.00008943969,0.01490484,0.0008356813,0.000005858267,0.9832636],"study_design_scores_gemma":[0.001396311,0.0002028882,0.006083566,0.0000664426,0.00003541008,0.00001295304,0.0001755024,0.003750403,0.977149,0.009895202,0.0009649089,0.0002674872],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0372823,0.00001723968,0.9612993,0.0001417071,0.0001712863,0.0003648232,0.000003258881,0.0001034445,0.0006166347],"genre_scores_gemma":[0.9723659,0.00001337399,0.02749668,0.00006702995,0.00001452822,0.00002355566,0.000002225776,0.000004633313,0.00001208174],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9829962,"threshold_uncertainty_score":0.411293,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06546444318962695,"score_gpt":0.3246996958231347,"score_spread":0.2592352526335077,"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."}}