Accurate and privacy preserving cough sensing using a low-cost microphone

Audio-based cough detection has become more pervasive in recent years because of its utility in evaluating treatments and the potential to impact the quality of life for individuals with chronic cough. We critically examine the current state of the art in cough detection, concluding that existing approaches expose private audio recordings of users and bystanders. We present a novel algorithm for detecting coughs from the audio stream of a mobile phone. Our system allows cough sounds to be reconstructed from the feature set, but prevents speech from being reconstructed intelligibly. We evaluate our algorithm on data collected in the wild and report an average true positive rate of 92% and false positive rate of 0.5%. We also present the results of two psychoacoustic experiments which characterize the tradeoff between the fidelity of reconstructed cough sounds and the intelligibility of reconstructed speech.

[1]  David H. Evans,et al.  Detection of cough signals in continuous audio recordings using hidden Markov models , 2006, IEEE Transactions on Biomedical Engineering.

[2]  I. Pavord,et al.  Prevalence, pathogenesis, and causes of chronic cough , 2008, The Lancet.

[3]  D. B. Keenan,et al.  Evaluation of an ambulatory system for the quantification of cough frequency in patients with chronic obstructive pulmonary disease: Cough 2005;1:3; published online as. doi:10.1186/1745-9974-1-3 , 2006 .

[4]  Karl Pearson F.R.S..  LIII. On lines and planes of closest fit to systems of points in space , 1901 .

[5]  Ramon Gisbert,et al.  Pharmacoeconomic evaluation of acute exacerbations of chronic bronchitis and COPD. , 2002, Chest.

[6]  S. Birring,et al.  ERS guidelines on the assessment of cough , 2007, European Respiratory Journal.

[7]  Ian Witten,et al.  Data Mining , 2000 .

[8]  A. A. Raj,et al.  Clinical assessment of chronic cough severity. , 2007, Pulmonary pharmacology & therapeutics.

[9]  Temitayo Ajayi,et al.  Ambulatory quantitative waking and sleeping cough assessment in patients with cystic fibrosis. , 2011, Journal of cystic fibrosis : official journal of the European Cystic Fibrosis Society.

[10]  N.‐J. Höglund,et al.  A method for determining the cough threshold with some preliminary experiments on the effect of codeine. , 1950 .

[11]  David W. McDonald,et al.  Activity sensing in the wild: a field trial of ubifit garden , 2008, CHI.

[12]  L. Boulet,et al.  Diagnosis and management of cough executive summary: ACCP evidence-based clinical practice guidelines. , 2006, Chest.

[13]  C. Burt,et al.  Ambulatory care visits to physician offices, hospital outpatient departments, and emergency departments: United States, 2001-02. , 2006, Vital and health statistics. Series 13, Data from the National Health Survey.

[14]  Jeff A. Bilmes,et al.  Conversation detection and speaker segmentation in privacy-sensitive situated speech data , 2007, INTERSPEECH.

[15]  D H Evans,et al.  The Leicester Cough Monitor: preliminary validation of an automated cough detection system in chronic cough , 2008, European Respiratory Journal.

[16]  S. Rane,et al.  Privacy Preserving Techniques for Speech Processing , 2010 .

[17]  M. Ringnér,et al.  Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks , 2001, Nature Medicine.

[18]  C. Burt,et al.  Ambulatory care visits to physician offices, hospital outpatient departments, and emergency departments: United States, 1999--2000. , 2004, Vital and health statistics. Series 13, Data from the National Health Survey.

[19]  K McGuinness,et al.  The Leicester Cough Monitor: a semi-automated, semi-validated cough detection system? , 2008, European Respiratory Journal.

[20]  D. B. Keenan,et al.  Evaluation of an ambulatory system for the quantification of cough frequency in patients with chronic obstructive pulmonary disease , 2005, Cough.

[21]  J Korpás,et al.  Objective assessment of cough suppressants under normal and pathological experimental conditions. , 1989, Drugs under experimental and clinical research.

[22]  Thomas Penzel,et al.  Mobile nocturnal long-term monitoring of wheezing and cough , 2007, Biomedizinische Technik. Biomedical engineering.

[23]  S. Schappert,et al.  Ambulatory care visits to physician offices, hospital outpatient departments, and emergency departments: United States, 1997. , 1997, Vital and health statistics. Series 13, Data from the National Health Survey.

[24]  N J HOGLUND,et al.  A method for determining the cough threshold with some preliminary experiments on the effect of codeine. , 1950, Acta physiologica Scandinavica.

[25]  J E DeLozier,et al.  National Ambulatory Medical Care Survey: 1989 summary. , 1991, Advance data.

[26]  Nicholas J Potter,et al.  Australian Cough Guidelines summary statement. , 2010, The Medical journal of Australia.

[27]  Ben Pinkowski.  Principal component analysis of speech spectrogram images , 1997, Pattern Recognit..

[28]  Hans Pasterkamp,et al.  Comparison of lung sound transducers using a bioacoustic transducer testing system. , 2006, Journal of applied physiology.

[29]  Alex Pentland,et al.  Face recognition using eigenfaces , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[30]  Samantha J Barry,et al.  The automatic recognition and counting of cough , 2006, Cough.

[31]  J. Korpáš,et al.  Analysis of the cough sound: an overview. , 1996, Pulmonary pharmacology.

[32]  H A BICKERMAN,et al.  The effect of a new bronchodilator aerosol on the air flow dynamics of the maximal voluntary cough of patients with bronchial asthma and pulmonary emphysema. , 1958, Journal of chronic diseases.

[33]  J. Smith,et al.  New Developments in the Objective Assessment of Cough , 2007, Lung.

[34]  T. Seemungal,et al.  Time course and recovery of exacerbations in patients with chronic obstructive pulmonary disease. , 2000, American journal of respiratory and critical care medicine.

[35]  S. Spencer,et al.  Time course of recovery of health status following an infective exacerbation of chronic bronchitis , 2003, Thorax.

[36]  John Adcock,et al.  Audio privacy: reducing speech intelligibility while preserving environmental sounds , 2008, ACM Multimedia.

[37]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[38]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[39]  D. Sanders,et al.  Return of FEV1 after pulmonary exacerbation in children with cystic fibrosis , 2010, Pediatric pulmonology.

[40]  Kevin McGuinness,et al.  Chronic cough: how do cough reflex sensitivity and subjective assessments correlate with objective cough counts during ambulatory monitoring? , 2007, Thorax.

[41]  Meng-Chieh Chiu,et al.  Playful bottle: a mobile social persuasion system to motivate healthy water intake , 2009, UbiComp.

[42]  Eduard I Pudel,et al.  CICADA: Cough in Children and Adults: Diagnosis and Assessment. Australian Cough Guidelines summary statement , 2010 .

[43]  Peter G Gibson,et al.  Relationship between cough, cough receptor sensitivity and asthma in children. , 2002, Pulmonary pharmacology & therapeutics.

[44]  E. Juniper,et al.  Validation of a parent-proxy quality of life questionnaire for paediatric chronic cough (PC-QOL) , 2010, Thorax.

[45]  F. Wilcoxon.  Individual Comparisons by Ranking Methods , 1945 .

[46]  H. Hotelling.  Analysis of a complex of statistical variables into principal components. , 1933 .

[47]  Eitan Kerem,et al.  Effectiveness of PTC124 treatment of cystic fibrosis caused by nonsense mutations: a prospective phase II trial , 2008, The Lancet.