Oesophageal Voice Harmonic to Noise Ratio Enhancement over UMTS Networks Using Kalman-EM

Oesophageal voice is characterized by its extremely low intelligibility. An algorithm based on Kalman Expectation Maximization (EM) has been developed. The noise presented in the model, state and measurement noise has been optimized in order to improve the algorithm results. The database consists of "a" phonemes of several patients having undergone a total laryngectomy. Additionally, the effect of the algorithm on the UMTS mobile communication context has been tested. The tests show that the algorithm gives the best results when it is used as state noise an oesophageal noise and brown noise as measurement noise. The global percentage enhancement is 75.78%.

[1]  Begoña García Zapirain,et al.  Esophageal voices: glottal flow restoration , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[2]  Kah-Chye Tan,et al.  Kalman-filtering speech enhancement method based on a voiced-unvoiced speech model , 1999, IEEE Trans. Speech Audio Process..

[3]  Thierry Dutoit,et al.  HNR EXTRACTION IN VOICED SPEECH, ORIENTED TOWARDS VOICE QUALITY ANALYSIS , 2005 .

[4]  Marcel Gabrea.  Robust adaptive Kalman filtering-based speech enhancement algorithm , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[5]  Kuldip K. Paliwal,et al.  A speech enhancement method based on Kalman filtering , 1987, ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[6]  Björn E. Ottersten,et al.  Kalman filtering for low distortion speech enhancement in mobile communication , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[7]  Ehud Weinstein,et al.  Iterative and sequential Kalman filter-based speech enhancement algorithms , 1998, IEEE Trans. Speech Audio Process..

[8]  Shayna Zelcer,et al.  Multidimensional voice program analysis (MDVP) and the diagnosis of pediatric vocal cord dysfunction. , 2002, Annals of allergy, asthma & immunology : official publication of the American College of Allergy, Asthma, & Immunology.

[9]  Jerry D. Gibson,et al.  Filtering of colored noise for speech enhancement and coding , 1991, IEEE Trans. Signal Process..