Skip to main content

Advertisement

Log in

Analysis of swallowing sounds using hidden Markov models

Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

In recent years, acoustical analysis of the swallowing mechanism has received considerable attention due to its diagnostic potentials. This paper presents a hidden Markov model (HMM) based method for the swallowing sound segmentation and classification. Swallowing sound signals of 15 healthy and 11 dysphagic subjects were studied. The signals were divided into sequences of 25 ms segments each of which were represented by seven features. The sequences of features were modeled by HMMs. Trained HMMs were used for segmentation of the swallowing sounds into three distinct phases, i.e., initial quiet period, initial discrete sounds (IDS) and bolus transit sounds (BTS). Among the seven features, accuracy of segmentation by the HMM based on multi-scale product of wavelet coefficients was higher than that of the other HMMs and the linear prediction coefficient (LPC)-based HMM showed the weakest performance. In addition, HMMs were used for classification of the swallowing sounds of healthy subjects and dysphagic patients. Classification accuracy of different HMM configurations was investigated. When we increased the number of states of the HMMs from 4 to 8, the classification error gradually decreased. In most cases, classification error for = 9 was higher than that of = 8. Among the seven features used, root mean square (RMS) and waveform fractal dimension (WFD) showed the best performance in the HMM-based classification of swallowing sounds. When the sequences of the features of IDS segment were modeled separately, the accuracy reached up to 85.5%. As a second stage classification, a screening algorithm was used which correctly classified all the subjects but one healthy subject when RMS was used as characteristic feature of the swallowing sounds and the number of states was set to = 8.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

References

  1. Aboofazeli M, Moussavi Z (2005) Analysis and classification of swallowing sounds using reconstructed phase space features. Proc IEEE Int Conf Acous Speech Sig Proc (ICASSP) 5:421–424

    Article  Google Scholar 

  2. Duda RO, Hart PE, Stork DG (2001) Pattern classification. Wiley, New York

    MATH  Google Scholar 

  3. Gnitecki J, Moussavi Z (2005) The fractality of lung sounds: a comparison of three waveform fractal dimension algorithms. J Chaos Solitons Fractals 26(4):1065–1072

    Article  MATH  Google Scholar 

  4. Gold B, Morgan N (1999) Speech and audio signal processing. Wiley, New York

    Google Scholar 

  5. Hamlet S, Penney D, Formolo J (1994) Stethoscope acoustics and cervical auscultation of swallowing. Dysphagia 9(1):63–68

    Article  Google Scholar 

  6. Katz MJ (1988) Fractals and the analysis of the waveforms. Comput Biol Med 18(3):145–156

    Article  Google Scholar 

  7. Lazareck L, Moussavi Z (2002) Adaptive swallowing sound segmentation by variance dimension. Proc Eur Med Biol Eng Conf (EMBES)

  8. Lazareck L, Moussavi Z (2004) Classification of normal and dysphagic swallows by acoustical means. IEEE Trans Biomed Eng 51(12):2103–2112

    Article  Google Scholar 

  9. Logemann JA (1998) Evaluation and treatment of swallowing disorders, Austin, TX, PRO-ED

  10. Moussavi Z, Flores D, Thomas G (2004) Heart sound cancellation based on multiscale products and linear prediction. Proc IEEE Eng Med Biol Conf pp. 3840–3843

  11. Moussavi ZK, Leopando MT, Pasterkamp H, Rempel G (2000) Computerized acoustical respiratory phase detection without airflow measurement. J Med Biolog Eng Comp 38(2):198–203

    Article  Google Scholar 

  12. Moussavi Z (2005) Assessment of swallowing sounds’ stages with hidden Markov model. Proc IEEE Eng Med Biol Conf

  13. Palmer JB, Kuhlemeier KV, Tippett DC, Lynch C (1993) A protocol for the videofluorographic swallowing study. Dysphagia 8(3):209–214

    Article  Google Scholar 

  14. Proakis JG, Manolakis DG (2006) Digital signal processing. Prentice-Hall, Upper saddle river

  15. Rabiner LR (1989) A tutorial on hidden Markov models and selected application in speech recognition. Proc IEEE 77(2):257–286

    Article  Google Scholar 

  16. Rempel G, Moussavi Z (2005) The effect of viscosity on the breath-swallow pattern of young people with cerebral palsy. Dysphagia 20(2):108–112

    Article  Google Scholar 

  17. Stadler BM, Swami A (1999) Analysis of multiscale products for step detection and estimation. IEEE Trans Info Theory 45(3):1043–1051

    Article  Google Scholar 

  18. Vice FL, Heinz JM, Giuriati G, Hood M, Bosma JF (1990) Cervical auscultation of suckle feeding in newborn infants. Dev Med Child Neurol 32:760–768

    Article  Google Scholar 

  19. Viterbi AJ (1967) Error bounds for deconvolutional codes and an asymptotically optimal decoding algorithm. IEEE Trans Info Theory IT-13:260–269

    Article  Google Scholar 

  20. Xu Y, Weaver JB, Hearly DM Jr, Lu J (1994) Wavelet transform domain filters: a spatially selective noise filtration technique. IEEE Trans Image Process 3(6):747–758

    Article  Google Scholar 

  21. Yadollahi A, Moussavi Z (2007) Feature selection for swallowing sounds classification. Proc 29th IEEE EMBS pp 3172–3175

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Zahra Moussavi.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Aboofazeli, M., Moussavi, Z. Analysis of swallowing sounds using hidden Markov models. Med Biol Eng Comput 46, 307–314 (2008). https://doi.org/10.1007/s11517-007-0285-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-007-0285-8

Keywords

Navigation