Pronunciation variations and context-dependent model to improve ASR performance for dyslexic children’s read speech

Focusing on the key element for an ASR-based application for dyslexic children reading isolated words in Bahasa Melayu, this paper can be an evidence of the need to have a carefully designed acoustic model for a satisfying recognition accuracy of 79.17% on test dataset. Pronunciation variations and context-dependent model are two main components of such acoustic model. This model adopts the most frequent errors in reading selected vocabulary, which are obtained from primary data collection and analysis.The analysis gives the most frequent spelling and reading errors as vowel substitution with over 20% of total errors made.

[1]  Satanjeev Banerjee,et al.  Evaluating the effect of predicting oral reading miscues , 2003, INTERSPEECH.

[2]  Johannes C. Ziegler,et al.  Do differences in brain activation challenge universal theories of dyslexia? , 2006, Brain and Language.

[3]  Eleanor L. Higgins,et al.  Speaking to Read: The Effects of Continuous vs. Discrete Speech Recognition Systems on the Reading and Spelling of Children with Learning Disabilities , 1999 .

[4]  Sheikh Hussain Shaikh Salleh,et al.  Neural network speaker dependent isolated Malay speech recognition system: handcrafted vs genetic algorithm , 2001, Proceedings of the Sixth International Symposium on Signal Processing and its Applications (Cat.No.01EX467).

[5]  M. Snowling.  Dyslexia, 2nd ed. , 2000 .

[6]  Peter G. Fairweather,et al.  Speech recognition, children, and reading , 1998, CHI Conference Summary.

[7]  Jwa K. Kim,et al.  Spelling errors as a window on variations in phonological deficits among students with dyslexia , 1999 .

[8]  Kamaruzaman Jusoff,et al.  Acoustic Pronunciation Variations Modeling for Standard Malay Speech Recognition , 2008, Comput. Inf. Sci..

[9]  Eleanor L. Higgins,et al.  Speaking to read: The effects of speech recognition technology on the reading and spelling performance of children with learning disabilities , 1999 .

[10]  Goldberg,et al.  Genetic algorithms , 1993, Robust Control Systems with Genetic Algorithms.

[11]  T. Whitlock.  Dyslexia , 1989, The Lancet.

[12]  Elmar Nöth,et al.  Improving Children's Speech Recognition by HMM Interpolation with an Adults' Speech Recognizer , 2003, DAGM-Symposium.

[13]  Ronald A. Cole,et al.  Advances in Children's Speech Recognition within an Interactive Literacy Tutor , 2004, HLT-NAACL.

[14]  Maryanne Wolf,et al.  What time may tell: Towards a new conceptualization of developmental dyslexia , 1999 .

[15]  Ingvar Lundberg,et al.  The Computer as a Tool of Remediation in the Education of Students with Reading Disabilities—A Theory-Based Approach , 1995 .

[16]  Peter G. Fairweather,et al.  Using Speech Recognition Technology to Enhance Literacy Instruction for Emerging Readers , 2000 .

[17]  Jørgen Frost.  Phonemic awareness, spontaneous writing, and reading and spelling development from a preventive perspective , 2001 .