Myanmar text-to-speech system with rule-based tone synthesis

Acoustical Science and Technology

Kyawt Yin Win¹  Tomio Takara¹ 

[1] Department of Information Engineering, University of the Ryukyus

关键词: Myanmar;    Tonal languages;    Text-to-speech;    Tone synthesis;    Normalization;    Rule-based;   

DOI  :  10.1250/ast.32.174

学科分类：声学和超声波

来源: Acoustical Society of Japan

【 摘 要 】

References(12)We have introduced a novel Myanmar text to speech (MyanmarTTS) system with rule-based tone synthesis. Myanmar is a tonal language that possesses unique characteristics compared with other tonal languages such as Chinese, Vietnamese and Thai. Such languages have complicated fundamental-frequency (F0) patterns of tones, and F0 is of foremost importance. Myanmar tones are unique in their simplistic pattern related not only to F0 but also, more specifically to duration. Myanmar tones have different durations between short-tone and long-tone groups. In accordance, we defined a tone rule employing two parameters F0 at the center of the syllable and the syllable’s duration. The rule is implemented with a linear F0 pattern. Large variability exists in the F0 and duration uttered by different speakers of different syllables. Hence, for tone synthesis, normalization of the F0 and duration is important and necessary to discriminate tones. We proposed a normalization method and the effectiveness of this method was confirmed in the distribution of the F0 and duration. The intelligibility of the synthesized tone was confirmed through listening tests with correct rates of 95.6% for male and 97.8% for female speech. As a result, we showed that the linear pattern is sufficient for Myanmar tone synthesis.

【 授权许可】

Unknown