S P I R E    L A B

Objectives:

Addressing the gap between technological advancements and clinical intervention tools by developing automatic/semi-automatic analytical tools for speech and voice data that can be used to assist in the objective, quantitatively based diagnosis and treatment of speech and language difficulties associated with Autism Spectrum Disorder (ASD).
Addressing the dire lack of clinical intervention tools accessible to individuals of a variety of linguistic, cultural, and socioeconomic backgrounds, as exists in India.
These applications will comprise programs that:

• Quantify severity of the influence of ASD on speech prosody, based on several prosodic parameters, including pitch, volume, speech rate and voice quality, as well as prediction of “naturalness” of the speech sample, based on perception data.
• Identify the components of speech prosody most severely affected for a particular individual, and serve as a tool to provide biofeedback to the individual with ASD (as well as to the clinician), by way of a video game-like interface, as in Visi-pitch®, SpeechPrompts® or staRt (Speech Therapist’s App for R Treatment).

Background and Motivation:

The increase in prevalence of communication disorder (CD) is alarming worldwide, according to Centers for Disease Control and Prevention (CDC) survey in 2012, 7.7% of children aged 3–17 years had a CD during the past 12 months in United States. The study conducted among the 400 children from birth to six years of age in Kerala, India, reported that 38 (9.5%) children have language delay. The survey done by All India Institute of Speech and Hearing (AIISH) in rural population in India find that the prevalence of individuals at risk of CD is 6.07%. While technological advancements have allowed for improved understanding of a variety of communication disorders, current diagnostic and intervention tools do not yet take advantage of this information, forming a gap between our understanding of various aspects of communicative behavior in CD and clinical application of this knowledge. At present, even the most technologically advanced therapy tools used in CD

• are based largely on qualitative (rather than quantitative) comparison of disordered speech with typical speech,
• lack methods of quantitatively assessing degree of impairment along various prosodic parameters, as described above, and
• are available only in English.

Recent developments in the finegrained detection of various signals that may differ systematically between individuals with CD and those with unimpaired language serve as a call for parallel improvement in the diagnostic and therapeutic tools used in speech and language intervention particularly in culturally and linguistically diverse regions such as India.

>>top<<