Text-dependent speaker recognition using the Fuzzy ARTMAP neural network

Speaker recognition is the process of automatically recognizing the speaker by analyzing individual information contained in the speech waves. In this paper, we discuss the development of an intelligent system for text-dependent speaker recognition. The system comprises two main modules, a wavelet-based signal-processing module for feature extraction of speech waves, and an artificial-neural-network-based classifier module to identify and categorize the speakers. Wavelet is used in de-noising and in compressing the speech signals. The wavelet family that we used is the Daubechies Wavelets. After extracting the necessary features from the speech waves, the features were then fed to a neural-network-based classifier to identify the speakers. We have implemented the Fuzzy ARTMAP (FAM) network in the classifier module to categorize the de-noised and compressed signals. The proposed intelligent learning system has been applied to a case study of text-dependent speaker recognition problem.

Temporal processing and reading disability

The present investigation examined thehypothesis that early auditory temporalprocessing deficits cause later specificreading disability by impairing phonologicalprocessing (Farmer & Klein 1995; Tallal1980, 1984). Temporal processing ability atschool entry was examined using Tallal'sRepetition Test in a large unselected sample ofover 500 children followed over subsequentyears. Although our data confirmed the presenceof certain non-speech auditory processingdeficits in children later classified asspecific reading-disabled, many findings wereclearly at odds with a causal interpretation ofthis relationship. (1) Reading-disabled (RD)children were impaired at school entry on thesubtest with long interstimulus intervals(ISIs) but not the critical short-ISIsubtest. (2) RD children were not inferior toreading-age (RA) controls. (3) A subgroup of RDchildren with evidence of temporal deficitswere no less proficient on later phonologicalor reading measures than RD children with noevidence of early temporal impairment. (4)Although there was a reliable concurrentcorrelation between temporal deficits andphonological awareness at school entry(suggesting a possible common causeexplanation), early temporal deficits did notpredict later phonological impairment,pseudoword processing difficulties, or specificreading disability. On the other hand, earlytemporal deficits did predict later oralreceptive vocabulary and reading comprehensionweaknesses. These findings suggest thatauditory temporal deficits in dyslexics may beassociated with the same dysphasic-typesymptoms observed by Tallal and her colleaguesin specific language-impaired populations, butdo not cause the core phonological deficitsthat characterize dyslexic groups.

Developmental language disorders and adolescent risk: a public-health advocacy role for speech pathologists?

Within the multi-disciplinary team concerned with child and adolescent development, speech pathologists are uniquely positioned to understand the nature and overall developmental significance of language acquisition in childhood and adolescence. Other disciplines contribute valuable insights about psychosocial development during the childhood and adolescent years. The field of developmental psychology, for example provides a large and convincing body of evidence about the role of academic success as a protective factor against a range of psychosocial harms, in particular substance misuse, truancy, early school leaving, and juvenile offending. In this paper, we argue that juvenile offending embodies the notion of "adolescent risk", but in Australia in particular, has been under-investigated with respect to possible associations with developmental language disorders and subsequent academic failure. We present findings pertaining to a sample of 30 male juvenile offenders completing community based orders. Performance on a range of oral language processing and production skills was poorer than that of a demographically similar comparison group. Our results confirm the need to conceptualize language within a broader risk and protective framework. We therefore emphasize the public health importance of early language competence, by virtue of the psychosocial protection it confers on young people with respect to the development of prosocial skills, transition to literacy and overall academic achievement. We argue that speech pathologists are best positioned to advocate at a policy level about the broader public health importance of oral language competence.