1. Home
  2. Issues
  3. Volume 29, Issue 1 (2018)
  4. Inverse Filtering of Speech Signal for D ...

Informatica


Inverse Filtering of Speech Signal for Detection of Vocal Fold Paralysis After Thyroidectomy
Volume 29, Issue 1 (2018), pp. 91–105
Pub. online: 1 January 2018      Type: Research Article      Open accessOpen Access
Received
1 May 2017
Accepted
1 March 2018
Published
1 January 2018

Abstract

The Autoregressive model-based digital inverse filtering technique is applied in non-invasive detection of vocal fold paralysis. The vocal tract filter is modelled using variable order (up to 20) AR model which is adequate to individual characteristics of human vocal properties. This postulates the more accurate estimation of the glottal flow, disturbances of which are direct evidence of the vocal fold paralysis.

References

 
Airaksinen, M., Raitio, T., Story, D., Alku, P. (2014). Quasi closed phase glottal inverse filtering analysis with weighted linear prediction. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 22(3), 596–607.
 
Ali, Z., Elamvazuthi, I., Alsulaiman, M. (2016). Detection of voice pathology using fractal dimension in multiresolution analysis of normal and disordered speech signals. Journal of Medical Systems, 40(20).
 
Alku, P., Magi, C. (2009). Closed phase covariance analysis based on constrained linear prediction for glottal inverse filtering. The Journal of the Acoustical Society of America, 125(5), 3289–3305.
 
Alku, P. (2011). Glottal inverse filtering analysis of human voice production – a review of estimation and parametrization methods of the glottal excitation and their applications. Sadhana, 36(5), 623–650.
 
Arroyave, R.O., Bonilla, F.V., Trejos, D.T. (2012). Acoustic analysis and non linear dynamics applied to voice pathology detection: a review. Recent Patents on Signal Processing, 2(2), 96–107.
 
Baljekar, P.N., Patil, H.A. (2012). A comparison of waveform fractal dimension techniques for voice pathology classification. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4461–4464.
 
Bergenfelz, A., Jansson, S., Kristoffersson, A., Mårtensson, H., Reihnér, E., Wallin, G., Lausen, I. (2008). Complications to thyroid surgery: results as reported in a database from a multicenter audit comprising 3660 patients. Langenbeck’s Archives of Surgery, 393(5), 667–673.
 
Cairns, D.A., Hansen, J.H.L., Riski, J.E. (1994). Detection of hypernasal speech using a nonlinear operator. In: Proceedings of the IEEE Conference on Engineering in Medicine and Biology Society, pp. 253–254.
 
Dejonckere, P., Wieneke, G.H. (1994). Spectral, cepstral and aperiodicity characteristics of pathological voice before and after phonosurgical treatment. Clinical Linguistics & Phonetics, 8(2), 161–169.
 
Dibazar, A.A., Narayanan, S., Berger, T.W. (2002). Feature analysis for automatic detection of pathological speech. In: Proceedings of the Second Joint EMBS/BMES Conference, Houston, USA, October 23–26, 2002, pp. 182–183.
 
Elsheikh, E., Quriba, A.S., El-Anwar, M.W. (2016). Voice changes after late recurrent laryngeal nerve identification thyroidectomy. Journal of Voice, 30(6), 762.e1–762.e9.
 
Fukazawa, T., el-Assuooty, A., Honjo, I. (1988). A new index for evaluation of the turbulent noise in pathological voice. Journal of Acoustical Society of America, 83(3), 1189–1193.
 
Giovanni, A., Ouaknine, M., Triglia, J.M. (1999). Determination of largest Lyapunov exponents of vocal signal: application to unilateral laryngeal paralysis. Journal of Voice, 13(3), 341–354.
 
Henry, L., Helou, L., Solomon, N., Howard, R.S., Gurevich-Uvena, J., Coppit, G., Stojadinovic, A. (2010). Functional voice outcomes after thyroidectomy: an assessment of the Dysphonia Severity Index (DSI) after thyroidectomy. Surgery, 147(6), 861–870.
 
Hillenbrand, J., Cleveland, R.A., Erickson, R.L. (1994). Acoustic correlates of breathy vocal quality. Journal of Speech and Hearing Research, 37(4), 769–777.
 
Jeannon, J.P., Orabi, A.A., Bruch, G.A., Abdalsalam, H.A., Simo, R. (2009). Diagnosis of recurrent laryngeal nerve palsy after thyroidectomy: a systematic review. International Journal of Clinical Practice, 63(4), 624–629.
 
Kafentzis, G.P., Stylianou, Y., Alku, P. (2011). Glottal inverse filtering using stabilised weighted linear prediction. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5408–5411.
 
Kasuya, H., Kobayashi, Y., Kobayashi, T., Ebihara, S. (1983). Characteristics of pitch period and amplitude perturbations in pathologic voice. In: Proceedings of International Conference on Acoustics, Speech, and Signal Processing ICASSP, pp. 1372–1375.
 
Kasuya, H., Ogawa, S., Mashima, K., Ebihara, S. (1986). Normalized noise energy as an acoustic measure to evaluate pahologic voice. Journal of Acoustical Society of America, 80(5), 1329–1334.
 
Kaukėnas, J. (1983). On estimation of ar model order and parameters. Statistical Problems of Control, 61, 46–60. (in Russian).
 
Kaukėnas, J., Tamulevičius, G. (2016). Analysis of autoregressive model adequacy for Lithuanian vowels. Proceedings of Lithuanian Mathematical Society (Series B), 57, 19–24 (in Lithuanian).
 
Koike, Y. (1967). Application of some acoustic measures for the evaluation of laryngeal dysfunction. Journal of Acoustical Society of America, 42(5), 1209.
 
Lieberman, P. (1963). Some acoustic measures of the fundamental periodicity of normal and pathologic larynges. Journal of Acoustical Society of America, 35(3), 344–353.
 
Lifante, J.C., Payet, C., Menegaux, F., Sebag, F., Kraimps, J.L., Peix, J.L., Pattou, F., Colin, C., Duclos, A. (2017). Can we consider immediate complications after thyroidectomy as a quality metric of operation? Surgery, 161(1), 156–165.
 
Mihai, R., Randolph, G.W. (2009). Thyroid surgery, voice and the laryngeal examination-time for increased awareness and accurate evaluation. World Journal of Endocrine Surgery, 1(1), 1–5.
 
Musholt, T.J., Musholt, P.B., Garm, J., Napiontek, U., Keilmann, A. (2006). Changes of the speaking and singing voice after thyroid or parathyroid surgery. Surgery, 140(6), 978–988.
 
Ortega, J., Cassinello, N., Dorcaratto, D., Leopaldi, E. (2009). Computerized acoustic voice analysis and subjective scaled evaluation of the voice can avoid the need for laryngoscopy after thyroid surgery. Surgery, 145(3), 265–271.
 
Page, C., Zaatar, R., Biet, A., Strunski, V. (2007). Subjective voice assessment after thyroid surgery: a prospective study of 395 patients. Indian Journal of Medical Sciences, 61(8), 448–454.
 
Panek, D., Skalski, A., Gajda, J., Tadeusiewicz, R. (2015). Acoustic analysis assessment in speech pathology detection. International Journal of Applied Mathematics and Computer Science, 25(3), 631–643.
 
de Pedro Netto, I., Fae, A., Vartanian, J.G., Barros, A.P., Correia, L.M., Toledo, R.N., Testa, J.R., Nishimoto, I.N., Kowalski, L.P., Carrara-de Angelis, E. (2006). Voice and vocal self-assessment after thyroidectomy. Head Neck, 28(12), 1106–1114.
 
Sinagra, D.L., Montesinos, M.R., Tacchi, V.A., Moreno, J.C., Falco, J.E., Mezzadri, N.A., Debonis, D.L., Curutchet, H.P. (2004). Voice changes after thyroidectomy without recurrent laryngeal nerve injury. Journal of American College of Surgeons, 199(4), 556–560.
 
Stojadinovic, A., Shaha, A.R., Orlikoff, R.F., Nissan, A., Kornak, M.-F., Singh, B., Boyle, J.O., Shah, J.P., Brennan, M.F., Kraus, D.H. (2002). Prospective functional voice assessment in patients undergoing thyroid surgery. Annals of Surgery, 236(6), 823–832.
 
Tamulevičius, G., Kaukėnas, J. (2016). Adequacy analysis of autoregressive model for Lithuanian semivowels. In: Proceedings of IEEE 4th Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE), pp. 1–4.
 
Tamulevičius, G., Kaukėnas, J. (2017). High-order autoregressive modeling of individual speaker’s qualities. In: Proceedings of IEEE 5th Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE). (Accepted for publishing).
 
Vaičiukynas, E., Verikas, A., Gelžinis, A., Bačauskienė, M., Minelga, J., Hålander, M., Padervinskis, E., Uloza, V. (2015). Fusing voice and query data for non-invasive detection of laryngeal disorders. Expert Systems With Applications, 42, 8445–8453.
 
Walker, J., Murphy, P. (2007). A review of glottal waveform analysis. In: Stylianou, Y., Faundez-Zanuy, M., Esposito, A. (Eds.), Progress in Nonlinear Speech Processing, Lecture Notes in Computer Science, Vol. 4391, pp. 1–21.
 
Yumoto, E., Gould, W.J., Baer, T. (1982). Harmonics to Noise Ratio as hoarseness index of degree of hoarseness. Journal of Acoustical Society of America, 71(6), 1544–1550.

Biographies

Rybakovas Andrius

A. Rybakovas is a PhD student in Vilnius University Medical Faculty, an abdominal surgeon in the Centre of Abdominal Surgery, Vilnius University Hospital Santaros Klinikos. Scientific interests include endocrine surgery, upper GI surgery.

Beiša Virgilijus

V. Beiša is a head of the Centre of Abdominal Surgery at Vilnius University Hospital Santaros Klinikos, professor. In 1989 he received a PhD degree in biomedical sciences, Vilnius University. In 2009 he received habilitated doctor degree in biomedical sciences. Scientific interests include endocrine surgery, surgical treatment of thyroid, parathyroid, adrenal gland, pancreatic endocrine tumors.

Strupas Kęstutis

K. Strupas is a head of Clinic of Gastroenterology, Nephrourology, and Surgery, professor. In 1989 he received a PhD degree in biomedical sciences, Vilnius University. In 1997 he received habilitated doctor degree in biomedical sciences. Starting from 2002 he is a chairman of Clinic for Visceral Surgery and Gastroenterology Medical Faculty Vilnius University, member of the Vilnius University Senate, director of Clinic for General and Visceral Surgery. Starting from 2014 he is a full member of the Lithuanian Academy of Sciences. Scientific interests include minimally invasive surgery, strategies of treatment in HPB surgery, transplantation. He published 366 scientific articles

Kaukėnas Jonas

J. Kaukėnas is a long-time employee of the Institute of Mathematics and Informatics (now Vilnius University Institute of Data Science and Digital Technologies). His main research areas were an analysis of random signals, analysis of heart rate, speech signal analysis, and modelling.

Tamulevičius Gintautas
gintautas.tamulevicius@mii.vu.lt

G. Tamulevičius is a researcher at the Vilnius University Institute of Data Science and Digital Technologies. Currently, he also is an associate professor at Vilnius Gediminas Technical University. His main research interests include speech signal modelling and its application for speech and speech emotion recognition, speech pathology detection.


Full article Related articles Cited by PDF XML
Full article Related articles Cited by PDF XML

Copyright
© 2018 Vilnius University
Open access article under the CC BY license.

Keywords
inverse filtering autoregressive model speech analysis vocal fold paralysis

Metrics
since January 2020
1337

Article info
views

653

Full article
views

493

PDF
downloads

208

XML
downloads


Share


RSS