Evaluation of Supervised Learning Algorithms Based on Speech Features as Predictors to the Diagnosis of Mild to Moderate Intellectual Disability

Due to age-bound onset of symptoms used for diagnosis of mild to moderate intellectual disability, early diagnosis of these problems has long been a difficult issue. The diagnosis includes tests pertaining to intellectual functioning and adaptive behaviours including communication skills etc. In this paper, it is proposed to use speech features as an early indicator of the disorder which can be used to train machine learning algorithms for differentiating between speech of normally developing children and children with intellectual disability. In this paper, speech abnormalities are quantified using acoustic parameters including Linear Predictive Cepstral Coefficients, Mel Frequency Cepstral Coefficients and spectral features in speech samples of 48 participants (24 with intellectual disability and 24 age-matched controls). A training dataset was created by extracting these features which was used for learning by various classifiers. The experiments show promising results where Support Vector Machine gives an accuracy of 98%. Consequently, a well-trained classification algorithm can be used as an aid in early detection of mild to moderate intellectual disability.

[1]  A. Hassiotis,et al.  A Systematic Review of Animal-Assisted Therapy on Psychosocial Outcomes in People with Intellectual Disability. , 2016, Research in developmental disabilities.

[2]  Frank K. Soong,et al.  DNN i-Vector Speaker Verification with Short, Text-Constrained Test Utterances , 2017, INTERSPEECH.

[3]  Lauriece L. Zittel,et al.  Children with Disabilities (5th ed.) , 2003 .

[4]  Giorgio Biagetti,et al.  An Investigation on the Accuracy of Truncated DKLT Representation for Speaker Identification With Short Sequences of Speech Frames , 2017, IEEE Transactions on Cybernetics.

[5]  Hervé Bourlard,et al.  Speech pattern discrimination and multilayer perceptrons , 1989 .

[6]  R. Cabanas.  Some findings in speech and voice therapy among mentally deficient children. , 1954, Folia phoniatrica.

[7]  J. Mclean,et al.  Communication forms and functions of children and adults with severe mental retardation in community and institutional settings. , 1999, Journal of speech, language, and hearing research : JSLHR.

[8]  Sazali Yaacob,et al.  Classification of speech dysfluencies with MFCC and LPCC features , 2012, Expert Syst. Appl..

[9]  Vennila Ramalingam,et al.  Unsupervised speaker segmentation with residual phase and MFCC features , 2009, Expert Syst. Appl..

[10]  Sazali Yaacob,et al.  Classification of Speech Dysfluencies Using LPC Based Parameterization Techniques , 2012, Journal of Medical Systems.

[11]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.

[12]  Giorgio Biagetti,et al.  Speaker Identification with Short Sequences of Speech Frames , 2015, ICPRAM.

[13]  Robert L. Schalock,et al.  Intellectual Disability: Definition, Classification, and Systems of Supports , 2009 .

[14]  Okko Johannes Räsänen,et al.  Random subset feature selection in automatic recognition of developmental disorders, affective states, and level of conflict from speech , 2013, INTERSPEECH.

[15]  R. Kail.  General slowing of information-processing by persons with mental retardation. , 1992, American journal of mental retardation : AJMR.

[16]  Giuliano Antoniol,et al.  Linear predictive coding and cepstrum coefficients for mining time variant information from software repositories , 2005, MSR.

[17]  U Kramer,et al.  Clinical characteristics of children referred to a child development center for evaluation of speech, language, and communication disorders. , 1996, Pediatric neurology.

[18]  I. Lehiste.  chapter 7 – Suprasegmental Features of Speech , 1976 .

[19]  R. Koul,et al.  Effects of repeated listening experiences on the perception of synthetic speech by individuals with mild-to-moderate intellectual disabilities , 2006, Augmentative and alternative communication.

[20]  C. Mervis,et al.  Language and communicative development in Williams syndrome. , 2007, Mental retardation and developmental disabilities research reviews.

[21]  G. Arbanas.  Diagnostic and Statistical Manual of Mental Disorders (DSM-5) , 2015 .

[22]  M. Rutter,et al.  Developmental language disorders--a follow-up in later adult life. Cognitive, language and psychosocial outcomes. , 2005, Journal of child psychology and psychiatry, and allied disciplines.

[23]  Stan Davis,et al.  Comparison of Parametric Representations for Monosyllabic Word Recognition in Continuously Spoken Se , 1980 .

[24]  Gaurav Aggarwal,et al.  Classification of intellectual disability using LPC, LPCC, and WLPCC parameterization techniques , 2019 .

[25]  Haizhou Li,et al.  Normalization of the Speech Modulation Spectra for Robust Speech Recognition , 2008, IEEE Transactions on Audio, Speech, and Language Processing.

[26]  L. Abbeduto,et al.  Relation between receptive language and cognitive maturity in persons with mental retardation. , 1991, American journal of mental retardation : AJMR.

[27]  J. Matson,et al.  An examination of specific communication deficits in adults with profound intellectual disabilities. , 2012, Research in developmental disabilities.

[28]  Biing-Hwang Juang,et al.  Fundamentals of speech recognition , 1993, Prentice Hall signal processing series.

[29]  Rose A. Sevcik,et al.  Using a speech-generating device to enhance communicative abilities for an adult with moderate intellectual disability. , 2008, Intellectual and developmental disabilities.

[30]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[31]  E. Merrill,et al.  Degree of associative relatedness and sentence processing by adolescents with and without mental retardation. , 1992, American journal of mental retardation : AJMR.