Intonation modeling of Mandarin Chinese using a superpositional approach
نویسندگان
چکیده
The intonation model is an important component in text-tospeech systems to obtain natural and expressive speech synthesis. In this paper we propose a superpositional model for Mandarin Chinese. The intonation model is composed of the syllable and the phrase component. The parameters of the model are estimated using JEMA, a training approach with many advantages related to robustness and precision. Parameter estimation and model training are combined into a loop to progressively refine both the parameterization and the model. The high correlation (0.82) between synthetic and original contours in the test data show the suitability of this approach for modeling Mandarin. Furthermore, the high scores got in subjective evaluation (MOS=4.06) confirm the objective results.
منابع مشابه
Perception of intonation in Mandarin Chinese.
There is a tendency across languages to use a rising pitch contour to convey question intonation and a falling pitch contour to convey a statement. In a lexical tone language such as Mandarin Chinese, rising and falling pitch contours are also used to differentiate lexical meaning. How, then, does the multiplexing of the F(0) channel affect the perception of question and statement intonation in...
متن کاملModeling Duration and Intonation in Mandarin Chinese Synthesis with a Neural Network
The prosody control plays an important role in the naturalness of synthesized speech. In previous work, great efforts have been made to generate rule-based or parameter-based prosodic models [6]. In order to capture the complex interaction of different relevant prosodic factors, neural networks were recently employed. This paper presents a new method of learning and modeling duration and intona...
متن کاملConfusability of Chinese Intonation
Do lexical tones interfere with the realization of intonation types? Given that tone and intonation both use F0 as a primary cue, can a listener reliably identify statements and questions when some of the channel capacity is taken up by lexical tones? We study this issue through a perception test on a carefully designed and obtained intonation corpus on Mandarin Chinese. Our study shows the fol...
متن کاملProsody generation in Chinese synthesis using the template of quantified prosodic unit and base intonation contour
This paper presents a prosody generation method for Chinese mandarin using the template of quantified prosodic unit and base intonation contour. This method uses the prosodic feature picked-up from the syllables in the prosody words by rule as the base unit, and integrates the prosody rules in the prosody words of Chinese mandarin and base intonation contour to achieve the prosody contours with...
متن کاملIntonation modeling for TTS using a joint extraction and prediction approach
This paper presents a joint extraction and prediction framework for intonation modeling. The intonation model is based on a superpositional approach using Bézier curves. The components are attached to minor phrase and accent group. A greedy algorithm performs succesive partitions on training data using linguistic information. The parameters related to each partition are obtained using a global ...
متن کامل