Pathological speech signal analysis using time-frequency approaches

Critical Reviews in Biomedical Engineering

Volumn 40, Issue 1, 2012, Pages 63-95

  Ghoraani, Behnaz ^a   Umapathy, Karthikeyan ^a   Sugavaneswaran, Lakshmi ^a   Krishnan, Sridhar ^a  

^a RYERSON UNIVERSITY   (Canada)

Author keywords

Classification; Feature extraction; Pathological speech detection; Time frequency features; Voice quality assessment

Indexed keywords

DISORDERED VOICE; PATHOLOGICAL SPEECH; PATHOLOGICAL SPEECH SIGNALS; PATHOLOGICAL STRUCTURES; PATHOLOGICAL VOICE; SPEECH SIGNALS; TIME FREQUENCY FEATURES; TIME-FREQUENCY APPROACH; TIME-FREQUENCY TECHNIQUES; VOICE QUALITY ASSESSMENT; VOICE THERAPY;

CLASSIFICATION (OF INFORMATION); PATIENT MONITORING;

FEATURE EXTRACTION;

ACCURACY; ACOUSTIC ANALYSIS; ALGORITHM; AMBIGUITY; ANALYTIC METHOD; DYSPHONIA; FOURIER TRANSFORMATION; HUMAN; MAJOR CLINICAL STUDY; METHODOLOGY; NOISE; PRIORITY JOURNAL; REVIEW; SIGNAL DETECTION; SPEECH ANALYSIS; TIME FREQUENCY APPROACH; VOICE ANALYSIS;

ALGORITHMS; DIAGNOSIS, COMPUTER-ASSISTED; HUMANS; REPRODUCIBILITY OF RESULTS; SENSITIVITY AND SPECIFICITY; SOUND SPECTROGRAPHY; SPEECH DISORDERS; SPEECH PRODUCTION MEASUREMENT;

EID: 84861389552     PISSN: 0278940X     EISSN: None     Source Type: Journal    
DOI: 10.1615/CritRevBiomedEng.v40.i1.40     Document Type: Review

References (107)

1. Sataloff RT. Professional voice: the science and art of clinical care. New York: Raven Press; 1991.
2. Carding P, Wade A. Managing dysphonia caused by misuse and abuse. BMJ. 2000;321:1544-1545.
3. Marasek K. An attempt to classify lx signals. In: Proceedings of the 4th European Conference on Speech Communication and Technology (EuroSpeech 95), September 1995, Madrid, Spain.18-21.
4. Moore C, Slevin N, Winstanley S. Characterising vowel phonation by fundamental spectral normalisation of lx-waveforms. Proceedings of the International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications. 1999;1:1-6.
5. Ritchings T, McGillion M, Moore C. Pathological voice quality assessment using artificial neural networks. Med Eng Phys. 2002;24:561-564.
6. Childers DG, Sung-Bae K. Detection of laryngeal function using speech and electroglottographic data. IEEE Trans Biomed Eng. 1992;39:19-25.
7. Allin S, Galeotti J, Stetten G, Dailey SH. Enhanced snake based segmentation of vocal folds. Proc IEEE Int Symp Biomed Imaging. 2004;1:812-815.
8. Palm C, Lehmann TM, Bredno J, Neuschaefer-Rube C, Klajman S, Spitzer K. Automated analysis of stroboscopic image sequences by vibration profiles. In: Proceedings of the International Conference on Advances in Quantitative Laryngoscopy, Voice and Speech Research. 2001.
9. Deliyski D. High-speed videoendoscopy: recent progress and clinical prospects. In: Proceedings of the International Conference on Advances in Quantitative Laryngology, Voice and Speech Research. 2006;7:1-12.
10. Parsa V, Jamieson D. Identification of pathological voices using glottal noise measures. J Speech Lang Hearing Res. 2000;43:469-485.
11. Hammarberg B, Fritzell G, Sundberg J, Wedin L. Perceptual and acoustic correlates of abnormal voice qualities. Acta Otolaryngol. 1980;90:441-451.
12. Klingholz F. Acoustic recognition of voice disorders: a comparative study, running speech versus sustained vowels. J Acoust Soc Am. 1990;87:2218-2224.
13. Qi Y, Hillman RE, Milstein C. The estimation of signal-to-noise ratio in continuous speech for disordered voices. J Acoust Soc Am. 1999;105:2532-2535.
14. Gomez-Vila P, Fernandez R, Rodellar V, Nieto V, Alvarez A, Mazaira R, Godino JL. Glottal source biometrical signature for voice pathology detection. Speech Commun. 2008;51:759-781.
15. Boyanov D, Hadjitodorov S. Acoustic analysis of pathological voices. a voice analysis system for the screening of laryngeal diseases. IEEE Eng Med Biol Mag. 1997;16:74-82.
16. Kasuya H, Ogawa S, Mashima K, Ebihara S. Normalized noise energy as an acoustic measure to evaluate pathological voice. J Acoust Soc Am. 1986;80:1329-1334.
17. Gelzinis A, Verikas A, Bacauskiene M. Automated speech analysis applied to laryngeal disease categorization. Comput Methods Prog Biomed. 2008;91:36-47.
18. Saenz-Lechon N, Godino-Llorente J, Osma-Ruiz V, Gomez-Vilda P. Methodological issues in the development of automatic systems for voice pathology detection. Biomed Signal Process Control. 2006;1:120-128.
19. Massachusetts Eye and Ear Infirmary. Voice disorders database, version 1.03. Lincoln Park, NJ: Kay Elemetrics Corporation; 1994.
20. Reilly R, Moran R, Lacy P. Voice pathology assessment based on a dialogue system and speech analysis. In: Proceedings of the American Association of Artificial Intelligence Fall Symposium on Dialogue Systems for Health Communication, 2004, Washington, D.C.104-109.
21. Marinaki M, Kotropoulos C, Pitas I, Maglaveras N. Automatic detection of vocal fold paralysis and edema. In: Proceedings of International Conference on Spoken Language Processing, October 2004, Jeju Island, South Korea. 537-540.
22. Reynolds DA. A Gaussian mixture modeling approach to text-independent speaker identification [dissertation]. Atlanta, GA: Georgia Institute of Technology; 1992.
23. Dibazar A, Narayanan S, Berger T. Feature analysis for automatic detection of pathological speech. In: Proceedings of the Second Joint EMBS/BMES Conference, November 2002, Houston, TX. p. 182-183.
24. Kasuya H, Endo Y, Saliu S. Novel acoustic measurements of jitter and shimmer characteristics from pathological voice. In: Proceedings of EUROSPEECH, 1993, Berlin, Germany. 1973-1976.
25. Koike Y. Application of some acoustic measures for the evaluation of laryngeal dysfunction. Studia Phonologica. 1971;7:45-50.
26. Koike Y, Takahashi H, Calcaterra TC. Acoustic measures for detecting laryngeal pathology. Acta Otolaryngol. 1977;84:105-117.
27. Kasua H, Ebihara S, Chiba T, Konno T. Characteristics of pitch period and amplitude perturbations in speech of patients with laryngeal cancer. Electronics Commun Jpn. 1982;65A:423-430.
28. Prosek R, Montgomery A, Walden B, Hawkins D. An evaluation of residue features as correlates of voice disorders. J Commun Disord. 1987;20:105-117.
29. Gavidia-Ceballos L, Hansen JHL. Direct speech feature estimation using an iterative EM algorithm for vocal fold pathology detection. IEEE Trans Biomed Eng. 1996;43:373-383.
30. Davis SB. Preliminary results using inverse filtering of speech for automatic evaluation of laryngeal pathology. J Acoust Soc Am. 1970;58:11-112.
31. Davis S. Acoustic characteristics of normal and pathological voices. In: Speech and language research and theory. NJ: Academic Press.1979;31:271-335.
32. Eskenazi L, Childers DG, Hicks DM. Acoustic correlates of vocal quality. J Acoust Soc Am. 1990;33:298-306.
33. Koike Y, Markel J. Application of inverse filtering for detecting laryngeal pathology. Ann Otolaryngol. 1975;84:117-124.
34. Hansen JHL, Gavidia-Ceballos L, Kaiser JF. A nonlinear operator-based speech feature analysis method with application to vocal fold pathology assessment. IEEE Trans Biomed Eng. 1998;45:300-313.
35. Rosa MO, Pereira JC, Grellet M. Adaptive estimation of residue signal for voice pathology diagnosis. IEEE Trans Biomed Eng. 2000;47:96-104.
36. Yumoto E, Gould WJ, Baer T. Harmonic-to-noise ratio as an index of the degree of hoarseness. J Acoust Soc Am. 1982;71:1544-1550.
37. d'Alessandro C, Yegnanarayana B, Darsinos V. Decomposition of speech signals into deterministic and stochastic components. In: Proceedings IEEE International Conference on Acoustics, Speech, and Signal Processing, 1995, Detroit, MI. 760-763.
38. de Krom G. A cepstrum-based technique for determining a harmonics-to-noise ratio in speech signals. J Speech Lang Hearing Res. 1993;36:224-266.
39. Yumoto E. The quantitative evaluation of hoarseness. a new harmonics to noise ratio method. Arch Otolaryngol. 1983;109:48-52.
40. Awan S, Frenkel M. Improvements in estimating the harmonics to noise ratio of voice," J Voice. 1994;8:255-262.
41. Boersma P. Accurate short-term analysis of the fundamental frequency and the harmonics-to-noise ratio of a sampled sound. In: Proceedings of the Institute of Phonetic Sciences, Amsterdam, Netherlands. 1993;17:97-110.
42. Severin F, Bozkurt B, Dutoit T. HNR extraction in voiced speech oriented towards voice quality analysis. In: Proceedings of 13th European Signal Processing Conference, September 2005, Antalya, Turkey.
43. Little M, McSharry P, Roberts S, Costello D, Moroz I. Exploiting nonlinear recurrence and fractal scaling properties for voice disorder detection. Biomed Eng Online. 2007:10.1186/1475-925X-6-23.
44. Hansen J, Gavidia-Ceballos L, Kaiser J. A nonlinear operator-based speech feature analysis method with application to vocal fold pathology assessment. IEEE Trans Biomed Eng. 1998;45:300-313.
45. Alonso J, de Leon J, Alonso I, Ferrer M. Automatic detection of pathologies in the voice by HOS-based parameters. EURASIP J on Appl Signal Processing. 2001;4:275-284.
46. Giovanni A, Ouaknine M, Triglia J. Determination of largest Lyapunov exponents of vocal signal: application to unilateral laryngeal paralysis. Journal of Voice. 1999;13:341-354.
47. Zhang Y, Jiang J, Biazzo L, Jorgensen M. Perturbation and nonlinear dynamic analyses of voices from patients with unilateral laryngeal paralysis. Journal of Voice. 2005;19:519-528.
48. Zhang Y, McGilligan C, Zhou L, Vig M, Jiang J. Nonlinear dynamic analysis of voices before and after surgical excision of vocal polyps. J Acoust Soc Am. 2004;115:2270-2277.
49. Moran R, Reilly R, de Chazal P, Lacy P. Telephony-based voice pathology assessment using automated speech analysis. IEEE Trans Biomed Eng. 2006;53:468-477.
50. Kent RD, Vorperian HK, Kent JF, Duffy JR. Voice dysfunction in dysarthria: application of the multidimensional voice program. J Commun Disord. 2003;36:281-306.
51. Bielamowicz S, Kreiman J, Gerratt B, Dauer M, Berke G. Comparison of voice analysis systems for perturbation measurement. J Speech Lang Hearing Res. 1996;39:126-134.
52. Corp KE. Multidimensional voice program (MDVP) [computer program]. Lincoln Park, NJ: Kay Elemetrics Corporation; 2008.
53. Teston B, Galindo B. A diagnostic and rehabilitation aid workstation for speech and voice pathologies. In: 4th Eurospeech Proceedings, 1995, 1883-1886.
54. Huang D, Lin S, O'Brien R. Dr. Speech Users Guide. Version 3.0. North Reading, MA: Tiger Electronics, Inc.; 1995.
55. Ivanov T. Methods for objective analysis of singer voices [dissertation]. 1993.
56. Michaelis D, Gramss T, Strube H. Glottal-to-noise excitation ratio a new measure for describing pathological voices. Acustica Acta Acustica. 1997;83:700-706.
57. Qi Y, Weinberg B, Bi N, Hess W. Minimizing the effect of period determination on the computation of amplitude perturbation in voice. J Acoust Soc Am. 1995;97:2525-2532.
58. Qi Y, Hillman R. Temporal and spectral estimations of harmonics-to-noise ratio in human voice signals. J Acoust Soc Am. 1997;102:537-543.
59. Benesty J, Sondhi M, Huang Y. Springer handbook of speech processing. New York: Springer; 2008.
60. Godino-Llorente J, Gomez-Vilda P. Automatic detection of voice impairments by means of short-term cepstral parameters and neural network based detectors. IEEE Trans Biomed Eng. 2004;51:380-384.
61. Rabiner L, Huang BH. Fundamentals of speech recognition. Englewood Cliffs, NJ: Prentice-Hall; 1993.
62. Leinonen L, Kangas J, Torkkola K, Juvas A. Dysphonia detected by pattern recognition of spectral composition. J Speech Hearing Res. 1992;35:287-295.
63. Rihkanen H, Leinonen L, Hiltunen T, Kangas J. Spectral pattern recognition of improved voice quality," J Voice. 1994;8:320-326.
64. Wouwer VD, Scheunders P, Dyck DV, Bodt MD, Wuyts F, Heyning PHVD. Wavelet-FILVQ classifier for speech analysis. In: Proceedings of International Conference on Pattern Recognition. 1996;4:214-218.
65. Manfredi C. Adaptive noise energy estimation in pathological speech signals. IEEE Trans Biomed Eng. 2000;47:1538-1543.
66. Parraga A, Zaro MA, Schuck A Jr. Quantitative assessment of the use of continuous wavelet transform in the analysis of the fundamental frequency disturbance of the synthetic voice. Med Eng Phys. 2002;24(7-8):553-559.
67. Schuck A Jr, Parraga A. On the use of the wavelet packet transform as a feature extractor for pathological voice assessement. In: Proceedings of 2nd European Medical and Biological Engineering Conference, December 2002, Vienna, Austria. vol. 3, 506-507.
68. Umapathy K, Krishnan S, Parsa V, Jamieson D. Discrimination of pathological voices using a time-frequency approach. IEEE Trans Biomed Eng. 2005;52:421-430.
69. Mallat SG, Zhifeng Z. Matching pursuits with time-frequency dictionaries. IEEE Trans Signal Process. 1993;41:3397-3415.
70. Huang N, Shen S. Hilbert-Huang transform and its applications. World Scientific; 2005.
71. Gastón S, Mara T, Hugo R. Pathological voice analysis and classification based on empirical mode decomposition. Lect Notes Comput Sci. 2010;5967:364-381.
72. Schlotthauer G, Torres M, Rufiner H. Voice fundamental frequency extraction algorithm based on ensemble empirical mode decomposition and entropies. In: Proceedings of International Congress of the International Federation for Medical and Biological Engineering. 2009;35:9844-987.
73. Maragos P, Kaiser K, Quatieri T. Energy separation in signal modulations with application to speech analysis. IEEE Trans Signal Process. 1993;41:3024-3051.
74. Torres M, Schlotthauer G, Rufiner H, Jackson-Menaldi M. Empirical mode decomposition. Spectral properties in normal and pathological voices. In: Proceedings of International Congress of the International Federation for Medical and Biological Engineering, 2009. 252-255.
75. Rilling G, Flandrin P, Goncalvés P. On empirical mode decomposition and its algorithms. In: Proceedings of IEEE-EURASIP Workshop, 2003, Grado, Italia.
76. Sugavaneswaran L, Umapathy K, Krishnan S. Exploiting the ambiguity domain for non-stationary biomedical signal classification. In: Proceedings of 32nd Annual International IEEE EMBS Conference, 31 August to 4 September 2010. 1934-1937.
77. Ghoraani B, Krishnan S. A joint time-frequency and matrix decomposition feature extraction methodology for pathological voice classification. EURASIP J Adv Signal Process. 2009:928974.
78. Schuck A, Wisbeck J. Dysphonic voice classification using wavelet packet transform and artificial neural network. The 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2003.
79. Shama K, Krishna A, Cholayya NU. Study of harmonics-to-noise ratio and critical-band energy spectrum of speech as acoustic indicators of laryngeal and voice pathology. EURASIP J Adv Signal Process. 2007:85286.
80. Wester M. Automatic classification of voice quality: comparing regression models and hidden markov models. In: Proceedings of Voicedata 1998, January 1998, Utretch, The Netherlands. 92-97.
81. Godino-Llorente J, Gomez-Vilda P, Nicolás Sáenz-Lechón, Blanco-Velasco M, Cruz-Roldan F, Ferrer MA. Discriminative methods for the detection of voice disorders. In: Proceedings of International Conference on Non-Linear Speech Processing, April 2005.
82. Kukharchik P, Kheidorov I, Bovbel E, Ladeev D. Speech signal processing based on wavelets and SVM for vocal tract pathology detection. Lect Notes Comput Sci. 2008;5099:192-199.
83. Goodwin MM. Adaptive signal models: theory, algorithms and audio applications. Norwell, MA: Kluwer Academic Publishers; 1998.
84. Jaggi S, Karl W, Mallat S, Willsky A. High resolution pursuit for feature extraction. J Appl Comput Harmonic Anal. 1998;5:428-449.
85. Mallat S. A wavelet tour of signal processing. San Diego, CA: Academic Press; 1998.
86. Cohen L. Time-frequency distributions-a review. Proc IEEE. 1989;77(7):941-981.
87. Hlawatsch F, Boudreaux-Bartels G. Linear and quadratic time-frequency signal representations. Signal Process Mag. 1992;9:21-67.
88. Gribonval R. Fast matching pursuit with multiscale dictionary of gaussian chirps. IEEE Trans Signal Process. 2001;9:994-1001.
89. Moore BCJ. An introduction to the psychology of hearing. Toronto: Academic Press; 1992.
90. Shafi I, Ahmad J, Shah SI, Kashif FM. Techniques to obtain good resolution and concentrated time-frequency distributions: a review. EURASIP J Adv Signal Process. 2009:673539.
91. Sejdíc E, Djurovíc I, Jiang J. Time-frequency feature representation using energy concentration: an overview of recent advances. Digit Signal Process. 2009;19:153-183.
92. Xiong G, Zhao H-C, Wang L-J, Liu J-B. The wide sense time-frequency representation based on the wavelet and its relation with Cohen's class. In: Microwave and Millimeter Wave Technology, 2004. ICMMT 4th International Conference on, Proceedings. 18-21 August 2004. 677-680.
93. Cohen L. Time-frequency analysis. New York: Prentice-Hall; 1995.
94. Kozek W, Hlawatsch F, Kirchauer H, Trautwein U. Correlative time-frequency analysis and classification of nonstationary random processes. In: Time-Frequency and Time-Scale Analysis, 1994, Proceedings of the IEEE-SP International Symposium; 1994:417-420.
95. Hamila R, Astola J, Cheikh FA, Gabbouj M, Renfors M. Teager energy and the ambiguity function. IEEE Trans Signal Process. 1999;47:260-262.
96. Amin MG, Belouchrani A, Zhang Y. The spatial ambiguity function and its applications. IEEE Signal Process Lett. 2000;7:138-140.
97. Hong Z, Zheng B. An adaptive-kernel design method based on ambiguity domain. In: Proceedings of the IEEE-SP International Symposium on Time-Frequency and Time-Scale Analysis. 197-200.
98. Garcia G, Ebrahimi T, Vesin J. Classification of EEG signals in the ambiguity domain for brain-computer interface applications. Digit Signal Process. 2002;1:301-305.
99. Amin MG, Belouchrani A. Blind source separation using the spatial ambiguity functions. IIn: Proceedings of the IEEE-SP International Symposium on Time-Frequency and Time-Scale Analysis. 413-416.
100. Gorthi SS, Rastogi P. Improved high-order ambiguity-function method for the estimation of phase from interferometric fringes. Opt Lett. 2009;34:2575-2577.
101. Auger F, Flandrin P. Improving the readability of time-frequency and time-scale representations by the reassignment method. IEEE Trans Signal Process. 1995;43:1068-1089.
102. Cohen L, Posch T. Positive time-frequency distribution functions. IEEE Trans Acoust. 1985;33:31-38.
103. Krishnan S, Rangayyan R, Bell G, Frank C. Adaptive time-frequency analysis of knee joint vibroarthrographic signals for noninvasive screening of articular cartilage pathology. IEEE Trans Biomed Eng. 2000;47:773-783.
104. Lee D, Seung H. Algorithms for non-negative matrix factorization. Adv Neural Inf Process Syst. 2001;13:556-562.
105. Ghoraani B, Krishnan S. Quantification and localization of features in time-frequency plane. Canadian Conference on Electrical and Computer Engineering (CCECE), 2008. Canadian Conference on, May 2008. 1207-1210.
106. Berry M, Browne M, Langville A, Pauca V, Plemmons R. Algorithms and applications for approximate nonnegative matrix factorization. Compute Stat Data Anal. 2007;52:155-173.
107. Lin C-J. Projected gradient methods for nonnegative matrix factorization. Neural Comput. 2007;19:2756-2779.