Weighted entropy cortical algorithms for isolated Arabic speech recognition

Cortical algorithms (CA) inspired by and modeled after the human cortex, have shown superior accuracy in few machine learning applications. However, CA have not been extensively implemented for speech recognition applications, in particular the Arabic language. Motivated to apply CA to Arabic speech recognition, we present in this paper an improved CA that is efficiently trained using an entropy-based cost function, and an entropy based weight update rule. We modify the strengthening and inhibiting rules originally employed in CA during feedback training with weighted entropy concepts. Preliminary results show the merit of the proposed modifications in the recognition of isolated Arabic speech and motivate follow on research.

[1]  S.H. El-Ramly,et al.  Neural networks used for speech recognition , 2002, Proceedings of the Nineteenth National Radio Science Conference.

[2]  John S. Denker,et al.  Strategies for Teaching Layered Networks Classification Tasks , 1987, NIPS.

[3]  Mohammed A. Al-Manie,et al.  Automatic speech segmentation using the Arabic phonetic database , 2009 .

[4]  F.W. Zaki,et al.  Hybrid Fuzzy HMM System for Arabic Connectionist Speech Recognition , 2006, Proceedings of the Twenty Third National Radio Science Conference (NRSC'2006).

[5]  Lawrence K. Saul,et al.  Large-margin feature adaptation for automatic speech recognition , 2009, 2009 IEEE Workshop on Automatic Speech Recognition & Understanding.

[6]  Hassan Satori,et al.  Investigation arabic speech recognition using CMU sphinx system , 2009, Int. Arab J. Inf. Technol..

[7]  H. Bourouba,et al.  New Hybrid System (Supervised Classifier/HMM) for Isolated Arabic Speech Recognition , 2006, 2006 2nd International Conference on Information & Communication Technologies.

[8]  Husni Al-Muhtaseb,et al.  Arabic broadcast news transcription system , 2007, Int. J. Speech Technol..

[9]  Hassan Satori,et al.  Introduction to Arabic Speech Recognition Using CMUSphinx System , 2007, ArXiv.

[10]  Bashir Al-Diri,et al.  An Arabic speech corpus: a database for Arabic speech recognition , 2004 .

[11]  Nathaniel Schmidt.  Daniel and Androcles , 1926 .

[12]  Mansour M. Alghmadi,et al.  KACST Arabic Phonetics Database , 2003 .

[13]  Fadi Biadsy,et al.  Google's cross-dialect Arabic voice search , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[14]  Amer Al-Nassiri,et al.  Arabic phoneme recognition using neural networks , 2006 .

[15]  Shiliang Sun,et al.  Multitask Multiclass Support Vector Machines , 2011, 2011 IEEE 11th International Conference on Data Mining Workshops.

[16]  Richard M. Stern,et al.  Acoustical Pre-processing for Robust Speech Recognition , 1989, HLT.

[17]  M.M. Awais,et al.  Recognition of Arabic phonemes using fuzzy rule base system , 2003, 7th International Multi Topic Conference, 2003. INMIC 2003..

[18]  Bashir Al-Diri,et al.  A speech recognition model based on tri-phones for the Arabic language , 2007 .

[19]  Philip Birch,et al.  On preprocessing of speech signals , 2008 .

[20]  Mikko H. Lipasti,et al.  A case for neuromorphic ISAs , 2011, ASPLOS XVI.

[21]  Valeri Mladenov,et al.  Neural networks used for speech recognition , 2010 .

[22]  Mikko H. Lipasti,et al.  Cortical columns: Building blocks for intelligent systems , 2009, 2009 IEEE Symposium on Computational Intelligence for Multimedia Signal and Vision Processing.

[23]  Mikko H. Lipasti,et al.  Automatic abstraction and fault tolerance in cortical microachitectures , 2011, 2011 38th Annual International Symposium on Computer Architecture (ISCA).

[24]  Mikko H. Lipasti,et al.  Profiling Heterogeneous Multi-GPU Systems to Accelerate Cortically Inspired Learning Algorithms , 2011, 2011 IEEE International Parallel & Distributed Processing Symposium.

[25]  Mikko H. Lipasti,et al.  Discovering Cortical Algorithms , 2018, IJCCI.

[26]  Paul E. Hasler,et al.  Empirical comparison of analog and digital auditory preprocessing for automatic speech recognition , 2002, 2002 IEEE International Symposium on Circuits and Systems. Proceedings (Cat. No.02CH37353).

[27]  I. Gondal,et al.  A hybrid neural network based speech recognition system for pervasive environments , 2004, 8th International Multitopic Conference, 2004. Proceedings of INMIC 2004..

[28]  W. H. T. Gairdner,et al.  The phonetics of Arabic , 1925 .

[29]  S. Elmougy,et al.  A comparison of combined classifier architectures for Arabic Speech Recognition , 2008, 2008 International Conference on Computer Engineering & Systems.

[30]  J. Winn,et al.  Brain , 1878, The Lancet.