Acoustic Similarity of Inner and Outer Circle Varieties of Child-Produced English Vowels.

Purpose This article compares acoustic data of normally developing children from two dominant and one nondominant variety of English in order to determine phonetic proximity. Method The study focuses on one variety of American English (AE), one British English (BE) variety, and one Jamaican English (JE) variety owing to the historical and sociopolitical influences of both dominant varieties on JE. The work examines the four corner vowels (/a/, /ɑ/, /u:/, and /i:/) of the specified varieties. Speech from children aged 8-11 years was processed to extract duration, intensity, and fundamental frequency as well as the first three formants (F1, F2, and F3) of each vowel. Results Analysis of the acoustic variables showed, for the first time, that child-produced JE is phonetically closer to the variety of BE studied, than it is to the American variety. The acoustic properties of the child-produced JE vowels were found to be similar to those of adult-produced vowels, suggesting that, as has been shown for adult speech, there appears to be a limited impact of AE on JE. Conclusions This is the first acoustic study of children's speech to show that, despite the proximity to BE, the Jamaican variety is clearly a distinct variety of English. As the first study comparing AE, BE, and JE, the article provides experimental evidence of the acoustic differences in the varieties and points to the implications for automatic speech recognition and educational applications for children who speak JE.

Cloud-Based Speech Technology for Assistive Technology Applications (CloudCAST).

The CloudCAST platform provides a series of speech recognition services that can be integrated into assistive technology applications. The platform and the services provided by the public API are described. Several exemplar applications have been developed to demonstrate the platform to potential developers and users.

An Innovative Speech-Based User Interface for Smarthomes and IoT Solutions to Help People with Speech and Motor Disabilities.

A better use of the increasing functional capabilities of home automation systems and Internet of Things (IoT) devices to support the needs of users with disability, is the subject of a research project currently conducted by Area Ausili (Assistive Technology Area), a department of Polo Tecnologico Regionale Corte Roncati of the Local Health Trust of Bologna (Italy), in collaboration with AIAS Ausilioteca Assistive Technology (AT) Team. The main aim of the project is to develop experimental low cost systems for environmental control through simplified and accessible user interfaces. Many of the activities are focused on automatic speech recognition and are developed in the framework of the CloudCAST project. In this paper we report on the first technical achievements of the project and discuss future possible developments and applications within and outside CloudCAST.