Thai intonation analysis in harmonic-frequency domain

The paper describes the Thai Intonation Analysis System (TIAS) for speaker-independent recognition that achieves 90-95% word accuracy by applying two techniques: intonation flow analysis and voice identity calculation. The intonation flow analysis considers spectrograms emphasizing their modification styles for the frequency peaks. The five styles of modification mapped to Thai tones are low, medium, falling, high, and rising respectively. However, there are some words where tones cannot be labeled correctly by the former because of speakers' amplitude, frequency, and uttering period differences. These limitations can be cured by applying the voice identity calculation that applies correlative coefficient relation to find voice identity of each compared spectrogram. The paper also reported experimental results for the task of intonation analysis with ten Thai numeral words uttered with three-time repetitions by ten male speaker. In this paper, the speech waveforms are adapted from time-domain signals to harmonic-frequency domain.