Zobrazeno 1 - 10
of 59
pro vyhledávání: '"Hung-Yan Gu"'
Autor:
Chyi-Yeu Lin, Li-Chieh Cheng, Chun-Chia Huang, Li-Wen Chuang, Wei-Chung Teng, Chung-Hsien Kuo, Hung-Yan Gu, Kuo-Liang Chung, Chin-Shyurng Fahn
Publikováno v:
International Journal of Advanced Robotic Systems, Vol 10 (2013)
The purpose of this research is to develop multi-talented humanoid robots, based on technologies featuring high-computing and control abilities, to perform onstage. It has been a worldwide trend in the last decade to apply robot technologies in theat
Externí odkaz:
https://doaj.org/article/38aa2cf5e4d345478e01244e53b265be
Publikováno v:
APSIPA
Web of Science
Web of Science
In the field of music information retrieval (MIR), audio spectrogram can carry a great deal of information about the music content so as to be a robust visual representation for music signal. Recently, many research literatures show that convolutiona
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bf222c931c24063558589141abcf9220
https://doi.org/10.1109/apsipaasc47483.2019.9023314
https://doi.org/10.1109/apsipaasc47483.2019.9023314
Autor:
Chen-Lin Tsai, Hung-Yan Gu
Publikováno v:
Journal of the Chinese Institute of Engineers. 36:371-381
In this article, a speech signal synthesis scheme based on harmonic-plus-noise model (HNM) is extended to provide the function of speaker-nonspecific timbre transformation. To transform synthetic speech's timbre, we have developed a formant-based fre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f8cbd674a9aee958820ba13686b83d30
https://doi.org/10.1080/02533839.2012.730267
https://doi.org/10.1080/02533839.2012.730267
Autor:
Jia-Kang He, Hung-Yan Gu
Publikováno v:
ICMLC
In this study, an algorithm having a nice dynamic-programming structure is proposed for unit selection. This algorithm considers the costs of pitch and duration transformations, and the costs of contextual and spectral discontinuities. Here, the voic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a09dc6cc28392bd48321d8ff2dcf9bf2
https://doi.org/10.1109/icmlc.2016.7872965
https://doi.org/10.1109/icmlc.2016.7872965
Autor:
Hung-Yan Gu, Chyi-Yeu Lin, Kuo-Liang Chung, Chih-Cheng Chang, Kai-Jay Lu, Li-Chieh Cheng, Chang-Kuo Tseng, Chin-Shyurng Fahn
Publikováno v:
Robotics and Autonomous Systems. 59:943-953
This research is aimed to devise an anthropomorphic robotic head with a human-like face and a sheet of artificial skin that can read a randomly composed simplified musical notation and sing the corresponding content of the song once. The face robot i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f81e1813882dace87b4ab8db1db7a833
https://doi.org/10.1016/j.robot.2011.07.001
https://doi.org/10.1016/j.robot.2011.07.001
Publikováno v:
Journal of the Chinese Institute of Engineers. 31:1189-1198
New browser windows automatically appear without clicking them when certain web sites are browsed by a user. The user does not desire to open such browser windows but is forced to look at them. Such automatic displays of browser windows sometimes con
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5ee63b22cfa375198d45f5cd8466d764
https://doi.org/10.1080/02533839.2008.9671473
https://doi.org/10.1080/02533839.2008.9671473
Autor:
Kai-Wei Jiang, Hung-Yan Gu
Publikováno v:
ICMLC
Pitch contours are important for synthesizing highly natural speech signal. In this paper, we study a new pitch-contour generation method. The proposed method combines ANN prediction module with global-variance matching (GVM) and real contour selecti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::768c4e1d14914465d5c0c05d47f86014
https://doi.org/10.1109/icmlc.2015.7340954
https://doi.org/10.1109/icmlc.2015.7340954
Autor:
Hung-Yan Gu
Publikováno v:
Software: Practice and Experience. 35:1027-1039
In this paper, a large-alphabet-oriented scheme is proposed for both Chinese and English text compression. Our scheme parses Chinese text with the alphabet defined by Big-5 code, and parses English text with some rules designed here. Thus, the alphab
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8d2173dd347c85bd8ba6dfea78bae252
https://doi.org/10.1002/spe.661
https://doi.org/10.1002/spe.661
Autor:
Hung-Yan Gu, Sung-Fung Tsai
Publikováno v:
ISCSLP
In this paper, the voice conversion method based on segmental Gaussian mixture models (GMMs) is further improved by adding the module of target frame selection (TFS). Segmental GMMs are meant to replace a single GMM of a large number of mixture compo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::436573992a12efad2ecba55340e29fb4
https://doi.org/10.1109/iscslp.2014.6936633
https://doi.org/10.1109/iscslp.2014.6936633
Publikováno v:
ICMLC
In this paper, a different HMM structure is proposed to model the context-dependent spectral characteristics of a speech unit in order to improve synthetic speech fluency. Instead of using decision trees, we reduce the huge amount of context combinat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::49e78924ef3acb649d8676abda8657c5
https://doi.org/10.1109/icmlc.2014.7009144
https://doi.org/10.1109/icmlc.2014.7009144