Current Trends in Signal Processing
Fuzzy Variable Frame Analysis for Speech Recognition
Abstract
AbstractRecent works in machine learning has focused on models such as support vector machine (SVM), artificial neural network (ANN) and long short-term memory (LSTM), for automatically controlling the generalization and parameterization of the optimization process. This paper presents a fuzzy interpretation frame analysis procedure using LSTM classifier for noisy speech at word level using thresholding and local maxima procedure at framing level for the recognition process. Front end MFCC procedure has been modified in the framing phase to reduce the number of noisy frames using thresholding at two level local maxima procedures. A comparative results of various classifiers like SVM with kernel function, ANN and LSTM are tabulated for recognition accuracies. A fuzzy interpretation at the framing level to calculate optimal frames has been presented in this paper. In the proposed work 20% of unwanted processing of frames is reduced that equally produces the accuracies obtained by fixed frame analysis. An investigation shows that the obtained features with LSTM decrease word error rate still by 1% as increasing the recognition accuracy from 98 to 99% approach.Keywords: Speech recognition, ANN, SVM, LSTM, Fuzzy variableCite this ArticleVani H.Y., Anusuya M.A. Fuzzy Variable Frame Analysis for Speech Recognition. Current Trends in Signal Processing. 2019; 9(3): 9–18p.References (34)
- L Rabiner , BH Juang . Fundamentals of Speech Recognition . Prentice-Hall; 22 April 1993. p. 544.
- Zheng-Hua Tan, Ivan Kraljevski . Joint variable frame rate and length analysis for speech recognition under adverse conditions. Computers and Electrical Engineering.40(7). 2139–2149p. 2014
- Samudravijaya K. Variable Frame size analysis for speech recognition . http://www.iitg.ac.in/samudravijaya/publ/ 04iconVframeSize.pdf.
- Ivan Kraljevski1, Zheng -Hua Tan . Variable Frame Rate and Length Analysis for Data Compression In Distributed Speech Recognition. Proceedings of IC - NIDC, 2014 4th IEEE International Conference on Network Infrastructure and Digital Content. Beijing, China. 19 –21 Sept. 2014
- EC-S Jung, KJ Han, H Seo, SS Narayanan, HG Kang. A variable frame length and rate algorithm based on the spectral Kurtosis measure for speaker verification . Interspeech 2010, Japan, 2754–2757p.
- Julien Epps Eric H. C. Choi . An energy search approach to variable frame rate front-end processing for robust ASR . Interspeech 2005, Eurospeech, 9th European Conference on Speech Communication and Technology, Lisbon, Portugal, September 4–8, 2005.
- Theodoros Giannakopoulos. A method for silence removal and segmentation of speech signals, implemented in Matlab . University of Athens, Athens, 2009;(2).
- MJF Gales et al. Support Vector Machines for Noise Robust ASR . http://citeseerx.ist.psu.edu/viewdoc/downl oad?doi=10.1.1.297.7857. Current Trends in Signal Processing Volume 9, Issue 3 ISSN: 2277-6176 (Online), ISSN: 2321-4252 (Print) CTSP (2019) 9-18 © STM Journals 2019. All Rights Reserved Page 17
- Ramin Halavat et al. Recognition of human speech phonemes using a novel fuzzy approach. Artificial Intelligence Lab 308, Computer Engineering Department, Sharif University of Technology, Tehran, Iran, 2007.
- Jakobovski (2019). Jakobovski/free - spoken-digit-dataset. [online] GitHub. Available from https://github.com/Jakobovski/free- spoken-digit-dataset [Accessed Dec. 2019]. doi:10.5281/zenodo.1342401.
- Osman Eray , Sezai Tokat , Serdar Iplikci . An application of speech recognition with support vector machines. 6th International Symposium on Digital Forensic and Security (ISDFS), 10.1109, 2018
- Aravind Ganapathiraju et al . Support Vector Machines for Speech Recognition . http://citeseerx.ist.psu.edu/viewdoc/downl oad?doi=10.1.1.131.6537
- Davis KH, et al. Automatic Recognition of Spoken Digits . The Journal of the Acoustical Society of America, 1952
- Katagiri S. Pattern Recognition in Speech and Language Processing . CRC Press ; 2003.
- Hu Y, Loizou P. Subjective evaluation and comparison of speech enhancement algorithms, Speech Communication . 2007;49:588–601.
- Hu, Y. and Loizou, P Evaluation of objective quality measures for speech enhancement IEEE Transactions on Speech and Audio Processing. 2008;16(1):229–238.
- MA Anusuya , SK Katti . Speech Recognition by Machine: A Review . International Journal of Computer Science and Information Security Vol. 6, No. 3:2009
- Patrick M. Mills Fuzzy Speech Recognition.
- Ramin Halavati . Evolution of Speech Recognizer A gents by Artificial Life . World Academy of Science, Engineering and Technology; 2005. p. 11.
- Ruben Solera -Ure˜na et al. SVMs for Automatic Speech Recognition, A Survey. LNCS 4391, Springer -Verlag, Workshop on Non linear Speech Processing (WNSP 2005)
- Yangyang Shi Mei -Yuh Hwang Xin Lei . End-To- End Speech Recognition Using a High Rank LSTM-CTC Based Model http://ssli.ee.washington.edu/mhwang/mob voi:2019
- Jayadev Billa . Dropout approaches for LSTM based speech recognition sy stems, IEEE International Conference on acoustics, Speech and Signal Processing (ICASSP). 2018.
- Kalpesh Krishna et.al Hierarchical Multitask Learning for CTC-Based Speech recognition, arXiv:1807.06234
- Yan-Hui Tu . A Hybrid Approach to combining conventional and deep learning techniques for single channel speech enhancement and Recognition. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) . 2018.
- Vani HY , Anusuya MA. Isolated Speech recognition using K -means and FCM Technique International Conference on Emerging Research in Electronics, Computer Science and Technology (ICERECT), 2015.
- Vani HY Anusuya MA . Noisy speech recognition using KFCM. International Conference on Cognitive Computing Information Processing. 2017.
- Jeen-Shing Wang, et al. A Cluster Validity Measure with Outlier Detection for Support Vector Clustering IEEE Transactions on Systems, MAN, And Cybernetics -Part B: Cybernetics vol. 38, no. 2008
- Salmela P . Neural Networks in Speech Recognition Tampere University of Technology, Publications; 2000. p. 295.
- Blankenstein, B . Artificial Neural Networks (ANN) . Department of CS, Washington University in St Louis, 2001
- Hosom JP et al. Speech Recognition Using Neural Networks” at the Center for Spoken Language Understanding, Turorail, 1999.
- Veera Ala -Keturi. Speech Recognition Based on Artificial Neural Network . Helsinki University of Technology.
- D. Tran, M. Wagner, Fuzzy hidden Markov models for speech and speaker recognition NAFIPS. 1999. pp. 426–430.
- LA Zadeh, From computing with numbers, to computing with words, a new paradigm Int. J. Appl. Math. 2002;12(3):307–324 Fuzzy Variable Frame Analysis for Speech Recognition Vani and Anusuya CTSP (2019) 9-18 © STM Journals 2019. All Rights Reserved Page 18
- Kurogi S . Speech recognition by an artificial neural network using findings on the afferent auditory system. Biological Cybernetics. 1991;64(3):243–249. Cite this Article Vani H.Y., Anusuya M.A . Fuzzy Variable Frame Analysis for Speech Recognition . Current Trends in Signal Processing. 2019; 9(3): 9–18p.