This paper introduces a Syllable HMM based Mandarin TTS system. 10-state left-to-right HMMs are used to model each syllable. We leverage the corpus and the front end of a concatenative TTS system to build the Syllable HMM based TTS system. Furthermore, we utilize the unique consonant/vowel structure of Mandarin syllable to improve the voiced/unvoiced decision of HMM states. Evaluation results s...

The idea of the composed syllable segments for syllable based concatenative speech synthesis is described in the paper. The use of the composed syllable segments essentially reduces the number of elementary segments that have to be extracted from samples to create the speech segment database. The experiments show that the quality of the synthesized speech that is obtained by using composed syll...

The study investigates the effect of speech rate on the temporal organization of syllable production of in Hong Kong Cantonese. The results show that all the component segments of the test syllables, including the vowel-nasal transitions and elementelement transitions in the diphthongs, contribute to the reduction of the entire syllable durations in fast speech. While the percentages of duratio...

Choice of the phonetic units speech recognizer is a factor greatly affecting the system performance. Phonetic units are normally defined according to the acoustic properties of a speech. Nevertheless, with the limit of training data, too delicate acoustic properties are ignored. Syllable structure is one of the properties usually ignored in English phonetic units due to a lot of possible onsets...

The syllable structure of Dschang is interesting for a variety of reasons. Most notable is the aspiration which can appear on most consonant types, including voiced stops. I shall argue that aspiration is best viewed as moraic, contributing to the weight of a syllable. An understanding of the syllable structure also gives valuable insights into the phonemic inventory and the distributional asym...

Korean subsyllabic structure was investigated by observing the pattern of responses arising from letter transpositions within a syllable in the Hangul script. Experiment 1 revealed no confusions when the onset and coda of one syllable of a disyllabic word were transposed. This was also the case in Experiment 2, where the transposition took place within a syllable having a coda composed of two c...

Previous work showed that tonal alignment distinguishes information status (given/new), that syllable structure affects alignment and that the scaling and alignment of tones correlate with focus. We investigate the interaction of these effects on the tonal realization of nuclear falling accents in German. In a production experiment, syllable structure [± open syllable] and voicing of the follow...

The classical approach in phonetics of careful observation of individual utterances can, this paper contends, be usefully augmented with automatic statistical analyses of large amounts of speech. Such analyses, using methods derived from speech recognition, are shown to quantify several known phonetic phenomena, most of which require syllable structure to be taken into account, and reveal some ...