Examining feature vector for phoneme recognition
Gražina Korvel, Bożena Kostek · 2017
The aim of this paper is to analyze usability of descriptors coming from music information retrieval to the phoneme analysis. The case study presented consists in several steps. First, a short overview of parameters utilized in speech analysis is given. Then, a set of time and frequency domain-based parameters is selected and discussed in the context of stop consonant acoustical characteristics. A toolbox created for this purpose in the Matlab environment is presented. The next analysis step includes the process of selecting the most discriminating descriptors based on Bron-Kerbosch algorithm. It is shown that parameters resulted from this analysis can be used for separation of consonants. Finally, phoneme recognition is performed employing k-NN classifier.