Automatic segmentation of separately pronounced Sinhala words into syllables

P G N Priyadarshani,N G J Dias

doi:10.4038/josuk.v6i0.4219

Abstract

Aligned corpora are widely used in various speech applications like automatic speech recognition, speech synthesis, as well as prosodic and phonetic research. The segmentation into syllables can be done manually or automatically. But it consumes significantly more time for a fully manual phonetic segmentation and practically it is a complicated task because in many cases it requires a large aligned speech corpus. If the manual syllabification is done by a group of individuals then the consistency is decreased because the analysis variations of the individuals. Consequently, there is a dire need for automatic syllabification and it is important because Sinhala language is syllable centric in nature. A method for syllabification of acoustic signals of separately pronounced Sinhala words has been given. Detecting the syllable boundaries was achieved by two main phases and those phases have been described with examples. Keywords: syllabification; oscillograph; vowel; consonant; envelope; thresholdDOI: http://dx.doi.org/10.4038/josuk.v6i0.4219 J Sci.Univ.Kelaniya 6 (2011) : 35-44

Highlights

All speech can be analyzed in terms of increasingly smaller and more refined units such as utterances, phrases, words, syllables, morphemes, phonemes
Used 1150 words containing all the vowels and consonants of the Sinhala language were selected from the Ven
As long as Automatic segmentation the inter syllable energy is lower than the energy of each syllable of the signal such as in the words flláh [kekatiya] and .evú,d [gædavila] in Figure 2 and Figure 3, it is possible to separate the acoustic signal into their syllables

Summary

Introduction

All speech can be analyzed in terms of increasingly smaller and more refined units such as utterances, phrases, words, syllables, morphemes, phonemes. A word can be divided into syllables and a syllable is a unit of speech that consists of at least one vowel. Consonants and vowels combine to make a syllable. /au/ and ft /aI/ (Kumara, 2009; rdcmlaË, 1997). C0n signifies to n consonants and V signifies a vowel including two diphthongs T! Further it can be considered a syllable as having onset, followed by a. P G N Priyadarshani vowel, and followed by a coda. For example .a [g] is the onset of the syllable .Eia [gæ:s] and ia [s] is the coda

Objectives

Methods

Results

Conclusion