Visual representation of the speech trace on a real time platform

Abstract

Through the present paper a methodology to adapt a set of algorithms and techniques derived from the field of adaptive signal processing on a real time platform, based on a specific digital signal processing board is presented. An overview of the algorithms implemented is followed by a brief presentation of the low-cost hardware platform developed, based on the TMS320C31, interfacing with a host PC through a PCI. A description of the encoding process followed to achieve real-time for practical applications is also given. Several experiments with a set of 11 English vowels show the possibilities and accuracy of the approximation. Applications of the resulting tool may be found in the field of speech training, language acquisition, phonetics, and other related fields.