Sage Journals: Discover world-class research

Abstract

Sub-vocal speech (SVS) recognition is highly desirable for silent communications among defence personnel and underwater operations. The SVS of Hindi phoneme has a great role to transform the sub-auditory signals into textual information for deaf Indians. Electromyography (EMG) has been applied to record signals of Hindi phoneme. EMG signals are picked up by placing electrodes over the neck areas below the chin of the subject. The SVS of Hindi phoneme recorded for four Hindi alphabets क (Ka), ख (Kha), ग (Ga) and घ (Gha) for 10 healthy Indian subjects. Two types of features; Wavelet based features and Auto Regressive (AR) coefficient features were extracted for these phonemes. Analysis has been made using three classifiers namely linear classifier, quadratic classifier and Support Vector Machine (SVM). Performances of all three classifiers are also evaluated in terms of accuracies. The classification accuracies averaged on 10 subjects with SVM classifier are found to be 75.00%, 78.05%, 80.50% and 81.30 % corresponding to phoneme क, ख, ग and घ respectively. Results also indicated that the wavelet based features with SVM classifier are best suited among three classifiers for accuracy of SVS Hindi phonemes discrimination. Myoelectric signals proved to have an important role for classification of sub-vocal Hindi phonemes in speech pattern recognition.

Keywords

Hindi phoneme sub-vocal speech wavelet transform electromyography Autoregressive

Get full access to this article

View all access options for this article.

References

Armas

W.D.

, Mamuna

K.A.

and Chau

, Vocal frequency estimation and voicing state prediction with surface EMG pattern recognition, Elsevier Speech Communication 64 (2014), 15–26.

Denby

, Schultz

, Honda

, Hueber

T.J.M.

, Gilbert

and Brumberg

, Silent speech interfaces, Elsiver Speech Communication 52 (2010), 270–287.

Betts

B.J.

and Jorgensen

, Small vocabulary recognition using surface electromyography in an acoustically harsh environment, Interacting with Computers 18 (2006), 1242–1259.

Jorgensen

and Binstead

, Web browser control using EMG based sub vocal speech recognition, Proc International Conference on System Sciences, 2005, pp. 294c–301c.

Jorgensen

, Lee

and Agabon

, Sub auditory speech recognition based on EMG signals, In Proc of International, Joint Conf on Neural Networks (IJCNN) (2003), 3128–3133.

Lee

K.S.

, EMG-based speech recognition using hidden markov models with global control variables, IEEE Transactions on Biomedical Engineering 53 (2008), 930–940.

Chan

A.D.C.

, Englehart

K.B.

, Hudgins

and Lovely

D.F.

, Multiexpert automatic speech recognition using acoustic and myoelectric signals, IEEE Transactions on Biomedical Engineering 4 (2006), 676–684.

Jahan

and Khan

, Sub-vocal phoneme-based EMG pattern recognition and its application in diagnosis, Annual IEEE Conference (INDICON), New Delhi, 2015, pp. 1–4. doi: 10.1109/INDICON.2015.7443564

Jahan

, Khan

, Sharma

S.K.

and Salhan

A.K.

, Feature extraction of EMG based sub-auditory vocal signals for rehabilitative applications, ISBN 978-93-84869-25-0, ETEEE Jamia Millia Islamia New Delhi (2015).

10.

Khan

and Jahan

, The application of AR coefficients and Burg method in sub-vocal EMG pattern recognition, Journal of Basic and Applied Engineering Research 10 (2015), 813–815.

11.

Farooq

and Datta

, Wavelet based robust sub-band features for phoneme recognition, IEE Proc-Vis Image and Signal Processing 3 (2004), 187–193.

12.

Pattichis

C.S.

and Elia

A.G.

, Autoregressive and cepstral analyses of motor unit action potentials, Medical Engineering & Physics 6 (1999), 405–419.

13.

Kang

W.J.

and Shiu

J.R.

, The application of cepstral coefficients and maximum likelihood method in EMG pattern recognition, IEEE Transactions on Biomedical Engineering 42 (1995), 777–785.

14.

Jose

A.G.

, Ricardo

, Robson

, Labidi

and Barros

A.K.

, Sub-vocal speech recognition based on EMG signal using independent component analysis and Neural Network MLP, IEEE Conference on Image and Signal Processing (2008), 221–224.

15.

Zhou

and Jiang

, Improved phoneme-based myoelectric speech recognition, IEEE Transactions on Biomedical Engineering 56 (2009), 2016–2023.

16.

Heris

H.K.

, Aghazaded

B.S.

and Bahrami

M.N.

, Optimal feature selection for the assessment of vocal fold disorders, Elsevier Computers in Biology and Medicine 10 (2009), 860–868.

17.

Huang

C.-N.

, Chen

C.-H.

and Chung

H.-Y.

, The review of applications and measurements in facial electromyography, Journal of Medical and Biological Engineering 1 (2004), 15–20.

18.

Scheme

E.J.

, Myoelectric signal classification for phoneme based speech recognition, IEEE Transactions on Biomedical Engineering 54 (2007), 694–699.

Classification of myoelectric signal for sub-vocal Hindi phoneme speech recognition

Abstract

Keywords

Get full access to this article

References