@InProceedings{8903138,
  author = {C. Bhat and S. K. Kopparapu},
  booktitle = {2019 27th European Signal Processing Conference (EUSIPCO)},
  title = {Identification of Alzheimer’s Disease using Non-linguistic Audio Descriptors},
  year = {2019},
  pages = {1-5},
  abstract = {Dementia is an overall term used to describe the reduced cognitive functioning in human beings, that is severe enough to impact their daily activities. Early diagnosis of dementia is imperative to provide timely treatment, either medication or therapy to alleviate the effects and sometimes slow the progression of dementia. In this work, we use speech processing and machine learning techniques to automatically classify speech into (a) healthy (HC) (b) with mild cognitive impairment (MCI) or (c) with Alzheimer's disease (AD). Only acoustic non-linguistic parameters are used for this purpose, making this a language independent approach. We evaluate our work using dementia and healthy speech from Pitt corpus of DementiaBank database. The performance of a three class Random Forest classifier is compared with our system comprising multiple two-class Random Forest classifiers cascaded to form a three class classifier, wherein a combination of approximate posterior probabilities is used to obtain a final class probability estimate. additional, patient speech is classified at segment level as well as at overall conversation level. Post processing on the patient speech classification at segment level provides a classification accuracy of 82% which is a significant absolute improvement of 8% over a simple three-class classifier performance.},
  keywords = {cognition;diseases;feature extraction;probability;signal classification;speech processing;support vector machines;Alzheimer's disease;nonlinguistic audio descriptors;dementia;reduced cognitive functioning;human beings;daily activities;early diagnosis;speech processing;nonlinguistic parameters;language independent approach;healthy speech;class Random Forest classifier;final class probability estimate;segment level;patient speech classification;three-class classifier performance;multiple two-class random forest classifiers;Dementia;Feature extraction;Acoustics;Random forests;Task analysis;Databases;Alzheimer’s disease;Dementia;classification;feature selection},
  doi = {10.23919/EUSIPCO.2019.8903138},
  issn = {2076-1465},
  month = {Sep.},
}

{"_id":"yGnTPbdv5oL4idWsF","bibbaseid":"bhat-kopparapu-identificationofalzheimersdiseaseusingnonlinguisticaudiodescriptors-2019","authorIDs":[],"author_short":["Bhat, C.","Kopparapu, S. K."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["C."],"propositions":[],"lastnames":["Bhat"],"suffixes":[]},{"firstnames":["S.","K."],"propositions":[],"lastnames":["Kopparapu"],"suffixes":[]}],"booktitle":"2019 27th European Signal Processing Conference (EUSIPCO)","title":"Identification of Alzheimer’s Disease using Non-linguistic Audio Descriptors","year":"2019","pages":"1-5","abstract":"Dementia is an overall term used to describe the reduced cognitive functioning in human beings, that is severe enough to impact their daily activities. Early diagnosis of dementia is imperative to provide timely treatment, either medication or therapy to alleviate the effects and sometimes slow the progression of dementia. In this work, we use speech processing and machine learning techniques to automatically classify speech into (a) healthy (HC) (b) with mild cognitive impairment (MCI) or (c) with Alzheimer's disease (AD). Only acoustic non-linguistic parameters are used for this purpose, making this a language independent approach. We evaluate our work using dementia and healthy speech from Pitt corpus of DementiaBank database. The performance of a three class Random Forest classifier is compared with our system comprising multiple two-class Random Forest classifiers cascaded to form a three class classifier, wherein a combination of approximate posterior probabilities is used to obtain a final class probability estimate. additional, patient speech is classified at segment level as well as at overall conversation level. Post processing on the patient speech classification at segment level provides a classification accuracy of 82% which is a significant absolute improvement of 8% over a simple three-class classifier performance.","keywords":"cognition;diseases;feature extraction;probability;signal classification;speech processing;support vector machines;Alzheimer's disease;nonlinguistic audio descriptors;dementia;reduced cognitive functioning;human beings;daily activities;early diagnosis;speech processing;nonlinguistic parameters;language independent approach;healthy speech;class Random Forest classifier;final class probability estimate;segment level;patient speech classification;three-class classifier performance;multiple two-class random forest classifiers;Dementia;Feature extraction;Acoustics;Random forests;Task analysis;Databases;Alzheimer’s disease;Dementia;classification;feature selection","doi":"10.23919/EUSIPCO.2019.8903138","issn":"2076-1465","month":"Sep.","bibtex":"@InProceedings{8903138,\n author = {C. Bhat and S. K. Kopparapu},\n booktitle = {2019 27th European Signal Processing Conference (EUSIPCO)},\n title = {Identification of Alzheimer’s Disease using Non-linguistic Audio Descriptors},\n year = {2019},\n pages = {1-5},\n abstract = {Dementia is an overall term used to describe the reduced cognitive functioning in human beings, that is severe enough to impact their daily activities. Early diagnosis of dementia is imperative to provide timely treatment, either medication or therapy to alleviate the effects and sometimes slow the progression of dementia. In this work, we use speech processing and machine learning techniques to automatically classify speech into (a) healthy (HC) (b) with mild cognitive impairment (MCI) or (c) with Alzheimer's disease (AD). Only acoustic non-linguistic parameters are used for this purpose, making this a language independent approach. We evaluate our work using dementia and healthy speech from Pitt corpus of DementiaBank database. The performance of a three class Random Forest classifier is compared with our system comprising multiple two-class Random Forest classifiers cascaded to form a three class classifier, wherein a combination of approximate posterior probabilities is used to obtain a final class probability estimate. additional, patient speech is classified at segment level as well as at overall conversation level. Post processing on the patient speech classification at segment level provides a classification accuracy of 82% which is a significant absolute improvement of 8% over a simple three-class classifier performance.},\n keywords = {cognition;diseases;feature extraction;probability;signal classification;speech processing;support vector machines;Alzheimer's disease;nonlinguistic audio descriptors;dementia;reduced cognitive functioning;human beings;daily activities;early diagnosis;speech processing;nonlinguistic parameters;language independent approach;healthy speech;class Random Forest classifier;final class probability estimate;segment level;patient speech classification;three-class classifier performance;multiple two-class random forest classifiers;Dementia;Feature extraction;Acoustics;Random forests;Task analysis;Databases;Alzheimer’s disease;Dementia;classification;feature selection},\n doi = {10.23919/EUSIPCO.2019.8903138},\n issn = {2076-1465},\n month = {Sep.},\n}\n\n","author_short":["Bhat, C.","Kopparapu, S. K."],"key":"8903138","id":"8903138","bibbaseid":"bhat-kopparapu-identificationofalzheimersdiseaseusingnonlinguisticaudiodescriptors-2019","role":"author","urls":{},"keyword":["cognition;diseases;feature extraction;probability;signal classification;speech processing;support vector machines;Alzheimer's disease;nonlinguistic audio descriptors;dementia;reduced cognitive functioning;human beings;daily activities;early diagnosis;speech processing;nonlinguistic parameters;language independent approach;healthy speech;class Random Forest classifier;final class probability estimate;segment level;patient speech classification;three-class classifier performance;multiple two-class random forest classifiers;Dementia;Feature extraction;Acoustics;Random forests;Task analysis;Databases;Alzheimer’s disease;Dementia;classification;feature selection"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2019url.bib","creationDate":"2021-02-11T19:15:22.163Z","downloads":0,"keywords":["cognition;diseases;feature extraction;probability;signal classification;speech processing;support vector machines;alzheimer's disease;nonlinguistic audio descriptors;dementia;reduced cognitive functioning;human beings;daily activities;early diagnosis;speech processing;nonlinguistic parameters;language independent approach;healthy speech;class random forest classifier;final class probability estimate;segment level;patient speech classification;three-class classifier performance;multiple two-class random forest classifiers;dementia;feature extraction;acoustics;random forests;task analysis;databases;alzheimer’s disease;dementia;classification;feature selection"],"search_terms":["identification","alzheimer","disease","using","non","linguistic","audio","descriptors","bhat","kopparapu"],"title":"Identification of Alzheimer’s Disease using Non-linguistic Audio Descriptors","year":2019,"dataSources":["NqWTiMfRR56v86wRs","r6oz3cMyC99QfiuHW"]}