{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T17:45:53Z","timestamp":1776534353738,"version":"3.51.2"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1011985","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2024,4,26]],"date-time":"2024-04-26T00:00:00Z","timestamp":1714089600000}}],"reference-count":33,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2024,4,16]],"date-time":"2024-04-16T00:00:00Z","timestamp":1713225600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100010269","name":"Wellcome Trust","doi-asserted-by":"publisher","award":["098418\/Z\/12\/A"],"award-info":[{"award-number":["098418\/Z\/12\/A"]}],"id":[{"id":"10.13039\/100010269","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010663","name":"H2020 European Research Council","doi-asserted-by":"publisher","award":["SOUNDSCENE"],"award-info":[{"award-number":["SOUNDSCENE"]}],"id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000690","name":"Research Councils UK","doi-asserted-by":"publisher","award":["BB\/N001818\/1"],"award-info":[{"award-number":["BB\/N001818\/1"]}],"id":[{"id":"10.13039\/501100000690","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Animal psychophysics can generate rich behavioral datasets, often comprised of many 1000s of trials for an individual subject. Gradient-boosted models are a promising machine learning approach for analyzing such data, partly due to the tools that allow users to gain insight into how the model makes predictions. We trained ferrets to report a target word\u2019s presence, timing, and lateralization within a stream of consecutively presented non-target words. To assess the animals\u2019 ability to generalize across pitch, we manipulated the fundamental frequency (F0) of the speech stimuli across trials, and to assess the contribution of pitch to streaming, we roved the F0 from word token to token. We then implemented gradient-boosted regression and decision trees on the trial outcome and reaction time data to understand the behavioral factors behind the ferrets\u2019 decision-making. We visualized model contributions by implementing SHAPs feature importance and partial dependency plots. While ferrets could accurately perform the task across all pitch-shifted conditions, our models reveal subtle effects of shifting F0 on performance, with within-trial pitch shifting elevating false alarms and extending reaction times. Our models identified a subset of non-target words that animals commonly false alarmed to. Follow-up analysis demonstrated that the spectrotemporal similarity of target and non-target words rather than similarity in duration or amplitude waveform was the strongest predictor of the likelihood of false alarming. Finally, we compared the results with those obtained with traditional mixed effects models, revealing equivalent or better performance for the gradient-boosted models over these approaches.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1011985","type":"journal-article","created":{"date-parts":[[2024,4,16]],"date-time":"2024-04-16T14:27:05Z","timestamp":1713277625000},"page":"e1011985","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":9,"title":["Gradient boosted decision trees reveal nuances of auditory discrimination behavior"],"prefix":"10.1371","volume":"20","author":[{"given":"Carla S.","family":"Griffiths","sequence":"first","affiliation":[]},{"given":"Jules M.","family":"Lebert","sequence":"additional","affiliation":[]},{"given":"Joseph","family":"Sollini","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6605-2362","authenticated-orcid":true,"given":"Jennifer K.","family":"Bizley","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2024,4,16]]},"reference":[{"issue":"2","key":"pcbi.1011985.ref001","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1038\/s41593-021-01007-z","article-title":"Mice alternate between discrete strategies during perceptual decision-making","volume":"25","author":"ZC Ashwood","year":"2022","journal-title":"Nature Neuroscience"},{"issue":"4","key":"pcbi.1011985.ref002","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1016\/j.neuron.2020.12.004","article-title":"Extracting the dynamics of behavior in sensory decision-making experiments","volume":"109","author":"International Brain Laboratory","year":"2021","journal-title":"Neuron"},{"key":"pcbi.1011985.ref003","unstructured":"Grinsztajn L, Oyallon E, Varoquaux G. Why do tree-based models still outperform deep learning on tabular data?; 2022. Available from: http:\/\/arxiv.org\/abs\/2207.08815."},{"key":"pcbi.1011985.ref004","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1007\/0-387-28958-5_8","volume-title":"Pitch: Neural Coding and Perception. Springer Handbook of Auditory Research","author":"CJ Darwin","year":"2005"},{"issue":"5","key":"pcbi.1011985.ref005","doi-asserted-by":"crossref","first-page":"2870","DOI":"10.1121\/1.4916690","article-title":"The role of spectral cues in timbre discrimination by ferrets and humans","volume":"137","author":"SM Town","year":"2015","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"6","key":"pcbi.1011985.ref006","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1250\/ast.27.349","article-title":"STRAIGHT, exploitation of the other aspect of VOCODER: Perceptually isomorphic decomposition of speech sounds","volume":"27","author":"H Kawahara","year":"2006","journal-title":"Acoustical Science and Technology"},{"key":"pcbi.1011985.ref007","volume-title":"Signal detection theory and psychophysics","author":"DM Green","year":"1966"},{"key":"pcbi.1011985.ref008","unstructured":"Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W, et al. LightGBM: a highly efficient gradient boosting decision tree. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. NIPS\u201917. Red Hook, NY, USA: Curran Associates Inc.; 2017. p. 3149\u20133157."},{"key":"pcbi.1011985.ref009","doi-asserted-by":"crossref","unstructured":"Akiba T, Sano S, Yanase T, Ohta T, Koyama M. Optuna: A Next-generation Hyperparameter Optimization Framework; 2019. Available from: http:\/\/arxiv.org\/abs\/1907.10902.","DOI":"10.1145\/3292500.3330701"},{"key":"pcbi.1011985.ref010","volume-title":"Advances in Neural Information Processing Systems","author":"SM Lundberg","year":"2017"},{"issue":"44","key":"pcbi.1011985.ref011","doi-asserted-by":"crossref","first-page":"11322","DOI":"10.1073\/pnas.1810766115","article-title":"Mammalian behavior and physiology converge to confirm sharper cochlear tuning in humans","volume":"115","author":"CJ Sumner","year":"2018","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"pcbi.1011985.ref012","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1145\/3556702.3556839","volume-title":"Proceedings of the Recommender Systems Challenge 2022. RecSysChallenge\u201922","author":"J Luo","year":"2022"},{"key":"pcbi.1011985.ref013","doi-asserted-by":"crossref","unstructured":"Machado MR, Karray S, de Sousa IT. LightGBM: an Effective Decision Tree Gradient Boosting Method to Predict Customer Loyalty in the Finance Industry. In: 2019 14th International Conference on Computer Science & Education (ICCSE); 2019. p. 1111\u20131116.","DOI":"10.1109\/ICCSE.2019.8845529"},{"key":"pcbi.1011985.ref014","unstructured":"Molnar C. 8.5 Permutation Feature Importance | Interpretable Machine Learning; 2023. Available from: https:\/\/christophm.github.io\/interpretable-ml-book\/feature-importance.html."},{"key":"pcbi.1011985.ref015","unstructured":"mcdermottLab\/pycochleagram; 2023. Available from: https:\/\/github.com\/mcdermottLab\/pycochleagram."},{"issue":"12","key":"pcbi.1011985.ref016","doi-asserted-by":"crossref","first-page":"1356","DOI":"10.1097\/00001756-199309150-00018","article-title":"Phonetic invariance in the human auditory cortex","volume":"4","author":"R Aulanko","year":"1993","journal-title":"Neuroreport"},{"issue":"9","key":"pcbi.1011985.ref017","doi-asserted-by":"crossref","first-page":"1875","DOI":"10.1162\/0899766054322964","article-title":"The cocktail party problem","volume":"17","author":"S Haykin","year":"2005","journal-title":"Neural Computation"},{"issue":"3","key":"pcbi.1011985.ref018","doi-asserted-by":"crossref","first-page":"528","DOI":"10.1086\/285553","article-title":"The Evolution of Nonhuman Primate Vocalizations: Effects of Phylogeny, Body Weight, and Social Context","volume":"142","author":"MD Hauser","year":"1993","journal-title":"The American Naturalist"},{"key":"pcbi.1011985.ref019","doi-asserted-by":"crossref","first-page":"893","DOI":"10.1016\/j.anbehav.2009.06.029","article-title":"The information content of giant panda, Ailuropoda melanoleuca, bleats: Acoustic cues to sex, age and size","volume":"78","author":"BD Charlton","year":"2009","journal-title":"Animal Behaviour"},{"issue":"1","key":"pcbi.1011985.ref020","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1121\/1.4768798","article-title":"Spectral timbre perception in ferrets: Discrimination of artificial vowels under different listening conditions","volume":"133","author":"JK Bizley","year":"2013","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"10","key":"pcbi.1011985.ref021","doi-asserted-by":"crossref","first-page":"e78607","DOI":"10.1371\/journal.pone.0078607","article-title":"Similarity of cortical activity patterns predicts generalization behavior","volume":"8","author":"CT Engineer","year":"2013","journal-title":"PloS One"},{"issue":"1684","key":"pcbi.1011985.ref022","first-page":"1003","article-title":"Zebra finches exhibit speaker-independent phonetic perception of human speech","volume":"277","author":"VR Ohms","year":"2010","journal-title":"Proceedings Biological Sciences"},{"issue":"24","key":"pcbi.1011985.ref023","doi-asserted-by":"crossref","first-page":"e2221756120","DOI":"10.1073\/pnas.2221756120","article-title":"Perceptual specializations for processing species-specific vocalizations in the common marmoset (Callithrix jacchus)","volume":"120","author":"MS Osmanski","year":"2023","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"pcbi.1011985.ref024","doi-asserted-by":"crossref","first-page":"e78278","DOI":"10.7554\/eLife.78278","article-title":"Vocalization categorization behavior explained by a feature-based auditory categorization model","volume":"11","author":"M Kar","year":"2022","journal-title":"eLife"},{"issue":"6","key":"pcbi.1011985.ref025","doi-asserted-by":"crossref","first-page":"1666","DOI":"10.1073\/pnas.1515380113","article-title":"Songbirds use spectral shape, not pitch, for sound pattern recognition","volume":"113","author":"MR Bregman","year":"2016","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"1","key":"pcbi.1011985.ref026","doi-asserted-by":"crossref","first-page":"e85405","DOI":"10.1371\/journal.pone.0085405","article-title":"Discrimination of Ultrasonic Vocalizations by CBA\/CaJ Mice (Mus musculus) Is Related to Spectrotemporal Dissimilarity of Vocalizations","volume":"9","author":"EG Neilans","year":"2014","journal-title":"PLOS ONE"},{"issue":"3","key":"pcbi.1011985.ref027","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1016\/j.anbehav.2008.01.026","article-title":"Does common spatial origin promote the auditory grouping of temporally separated signal elements in grey treefrogs?","volume":"76","author":"MA Bee","year":"2008","journal-title":"Animal Behaviour"},{"issue":"2","key":"pcbi.1011985.ref028","doi-asserted-by":"crossref","first-page":"1088","DOI":"10.1152\/jn.00884.2003","article-title":"Primitive Auditory Stream Segregation: A Neurophysiological Study in the Songbird Forebrain","volume":"92","author":"MA Bee","year":"2004","journal-title":"Journal of Neurophysiology"},{"issue":"1","key":"pcbi.1011985.ref029","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1037\/0735-7036.111.1.3","article-title":"Auditory scene analysis by songbirds: stream segregation of birdsong by European starlings (Sturnus vulgaris)","volume":"111","author":"SH Hulse","year":"1997","journal-title":"Journal of Comparative Psychology (Washington, DC: 1983)"},{"issue":"5","key":"pcbi.1011985.ref030","doi-asserted-by":"crossref","first-page":"1242","DOI":"10.1111\/ejn.13794","article-title":"Release from informational masking by auditory stream segregation: perception and its neural correlate","volume":"51","author":"LV Dolle\u017eal","year":"2020","journal-title":"The European Journal of Neuroscience"},{"issue":"2","key":"pcbi.1011985.ref031","doi-asserted-by":"crossref","first-page":"674","DOI":"10.1121\/1.4941322","article-title":"Cues for auditory stream segregation of birdsong in budgerigars and zebra finches: Effects of location, timing, amplitude, and frequency","volume":"139","author":"ML Dent","year":"2016","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"6","key":"pcbi.1011985.ref032","doi-asserted-by":"crossref","first-page":"EL246","DOI":"10.1121\/1.4954378","article-title":"Mistuning detection performance of ferrets in a go\/no-go task","volume":"139","author":"NY Homma","year":"2016","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"1591","key":"pcbi.1011985.ref033","doi-asserted-by":"crossref","first-page":"919","DOI":"10.1098\/rstb.2011.0355","article-title":"Properties of auditory stream formation","volume":"367","author":"BCJ Moore","year":"2012","journal-title":"Philosophical Transactions of the Royal Society of London Series B, Biological Sciences"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1011985","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2024,4,26]],"date-time":"2024-04-26T00:00:00Z","timestamp":1714089600000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1011985","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,26]],"date-time":"2024-04-26T13:42:57Z","timestamp":1714138977000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1011985"}},"subtitle":[],"editor":[{"given":"Fr\u00e9d\u00e9ric E.","family":"Theunissen","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2024,4,16]]},"references-count":33,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,4,16]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1011985","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.06.16.545302","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,16]]}}}