Search

Your search keyword '"Dong, Minghui"' showing total 498 results
Start Over Author "Dong, Minghui"
498 results on '"Dong, Minghui"'

106. Formant excursion in singing synthesis

Author

Chan, Paul Yaozhu, primary, Dong, Minghui, additional, Lim, Yi Qian, additional, Toh, Ashleigh, additional, Chong, Elliot, additional, Yeo, Mantita, additional, Chua, Megan, additional, and Li, Haizhou, additional

Published
2015
Full Text
View/download PDF

118. Combining documentation and research:ongoing work on an endangered language

Author

Xiong, Deyi, Castelli, Eric, Dong, Minghui, Thi Ngoc Yen, Pham, Michaud, Alexis, Guillaume, Séverine, Hardie, Andrew, Toda, Martine, Xiong, Deyi, Castelli, Eric, Dong, Minghui, Thi Ngoc Yen, Pham, Michaud, Alexis, Guillaume, Séverine, Hardie, Andrew, and Toda, Martine

Abstract

This paper is intended for an audience of speech technology specialists who believe that "automatic processing of under-resourced languages is a way to study language diversity with a multi-disciplinary view" (L. Besacier, keynote speech at this conference). It aims (i) to provide an illustration of the way in which data are collected in fieldwork on endangered languages, bringing attention to the quality of the transcriptions and annotations created by linguists, (ii) to present the contents and format of a set of endangered-language documents synchronizing sound and text, which are currently available online, and (iii) to sketch out some of the research purposes and applications to which these documents lend themselves, and which we intend to pursue in future work.

Published
2012

120. High quality voice conversion using prosodic and high-resolution spectral features.

Author

Nguyen, Hy, Lee, Siu, Tian, Xiaohai, Dong, Minghui, and Chng, Eng

Subjects
PROSODIC analysis (Linguistics), PSYCHOACOUSTICS, HUMAN voice, ORATORS, HUMAN facial recognition software
Abstract

Voice conversion methods have advanced rapidly over the last decade. Studies have shown that speaker characteristics are captured by spectral feature as well as various prosodic features. Most existing conversion methods focus on the spectral feature as it directly represents the timbre characteristics, while some conversion methods have focused only on the prosodic feature represented by the fundamental frequency. In this paper, a comprehensive framework using deep neural networks to convert both timbre and prosodic features is proposed. The timbre feature is represented by a high-resolution spectral feature. The prosodic features include F0, intensity and duration. It is well known that DNN is useful as a tool to model high-dimensional features. In this work, we show that DNN initialized by our proposed autoencoder pretraining yields good quality DNN conversion models. This pretraining is tailor-made for voice conversion and leverages on autoencoder to capture the generic spectral shape of source speech. Additionally, our framework uses segmental DNN models to capture the evolution of the prosodic features over time. To reconstruct the converted speech, the spectral feature produced by the DNN model is combined with the three prosodic features produced by the DNN segmental models. Our experimental results show that the application of both prosodic and high-resolution spectral features leads to quality converted speech as measured by objective evaluation and subjective listening tests. [ABSTRACT FROM AUTHOR]

Published
2016
Full Text
View/download PDF

121. Effects of Drying Methods on the Aroma Components and Quality of C apsella Bursa-Pastoris L.

Author

Zhang, Li, Liu, Tengfei, Xue, Yanjun, Liu, Chen, Ru, Hua, Dong, Minghui, and Yu, Zhifang

Subjects
BRASSICACEAE, MICROWAVE drying, FREEZE-drying, FOOD aroma, CHLOROPHYLL, GAS chromatography/Mass spectrometry (GC-MS)
Abstract

C apsella bursa-pastoris L. ( C . bursa-pastoris) was treated by hot air drying, microwave drying, vacuum drying and freeze-drying, respectively, to analyze the influences on aroma components using gas chromatography-mass spectrometry. The results showed that the freeze-dried product enjoyed significantly alleviated color changes, short rehydration time, high rehydration ratio and retention rates of chlorophyll and vitamin C. Vacuum drying functioned inferior to freeze-drying but superior to hot air drying and microwave drying. As for aroma components, both vacuum drying and freeze-drying managed to preserve the characteristic aroma components in C . bursa-pastoris. In summary, vacuum drying and freeze-drying retained the color, texture, morphology as well as grass and leaf aromas of C . bursa-pastoris in maximum, but the former method, which lasts a shorter time and consumes less energy, should be given first priority in large-scale industrial practice. Practical Applications C . bursa-pastoris suffers from a plummet of nutritional value and loss of economic benefits even within short harvest and storage periods. Drying newly harvested C . bursa-pastoris with appropriate techniques can both meet different consumer demands and effectively prolong the shelf life of products. Various drying techniques are bound to affect sensory attributes and retention rates of nutrients and aroma components significantly. We treated fresh C . bursa-pastoris by vacuum drying, hot air drying, microwave drying and freeze-drying, and compared the quality of final products, aiming to find out the optimum drying method and parameters and while providing valuable practical evidence for industrial drying of this vegetable. [ABSTRACT FROM AUTHOR]

Published
2016
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results