Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Langzhou Chen"'
Autor:
Langzhou Chen, Volker Leutnant
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::368de0d2aa24e8166ddef2977ac852fb
https://doi.org/10.21437/interspeech.2019-2818
https://doi.org/10.21437/interspeech.2019-2818
Publikováno v:
IEEE Journal of Selected Topics in Signal Processing. 8:323-335
Generating expressive, naturally sounding, speech from text using a speech synthesis (TTS) system is a highly challenging problem. However for tasks such as audiobooks it is essential if their use is to become widespread. Generating expressive speech
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1f531dc7ffc5044495337d94ea39fb3f
https://doi.org/10.1109/jstsp.2013.2294938
https://doi.org/10.1109/jstsp.2013.2294938
Autor:
Kayoko Yanagisawa, Langzhou Chen, Vincent Wan, Norbert Braunschweiler, Masami Akamine, Javier Latorre, Mark J. F. Gales
Publikováno v:
IEEE Journal of Selected Topics in Signal Processing. 8:296-306
The statistical models of hidden Markov model based text-to-speech (HMM-TTS) systems are typically built using homogeneous data. It is possible to acquire data from many different sources but combining them leads to a non-homogeneous or diverse datas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1fb6777263263ad23cf96c9b4043c4dc
https://doi.org/10.1109/jstsp.2013.2295058
https://doi.org/10.1109/jstsp.2013.2295058
Publikováno v:
ICASSP
In this paper we investigate the use of noise-robust features characterizing the speech excitation signal as complementary features to the usually considered vocal tract based features for Automatic Speech Recognition (ASR). The proposed Excitation-b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2e1afd10c2b9cd391c6d51b7266c29fb
https://doi.org/10.1109/icassp.2015.7178855
https://doi.org/10.1109/icassp.2015.7178855
Expressive synthesis from text is a challenging problem. There are two issues. First, read text is often highly expressive to convey the emotion and scenario in the text. Second, since the expressive training speech is not always available for differ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::41e9da1fefd1d1df686c71fad8e1e058
https://www.repository.cam.ac.uk/handle/1810/247404
https://www.repository.cam.ac.uk/handle/1810/247404
Autor:
K. K. Chin, Mark J. F. Gales, Langzhou Chen, Kate Knill, Catherine Breslin, Vincent Wan, Xie Chen
Publikováno v:
INTERSPEECH
Xie Chen would like to thank Toshiba Research Europe Ltd, Cambridge Research Lab, for funding his work. The authors would like to thank the Toshiba Cambridge Speech Group for allowing the data to be collected, also would like to thank Chao Zhang and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f092c00bce017512b73f24087adb9af1
https://doi.org/10.21437/interspeech.2014-253
https://doi.org/10.21437/interspeech.2014-253
Publikováno v:
INTERSPEECH
Copyright © 2014 ISCA. In practical scenarios for speaker adaptation of speech synthesis systems, the quality of adaptation audio data may be poor. In these situations, it is necessary to make use of the available audio to capture the speaker attrib
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fd198c57db3474686e782c806bfa4323
https://doi.org/10.21437/interspeech.2014-364
https://doi.org/10.21437/interspeech.2014-364
Autor:
Norbert Braunschweiler, Langzhou Chen
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4d69e5a3b853757a7b73a804fc0762dd
https://doi.org/10.21437/interspeech.2014-195
https://doi.org/10.21437/interspeech.2014-195
Publikováno v:
ICASSP
Automatically generating expressive speech from plain text is an important research topic in speech synthesis. Given the same text, different speakers may interpret it and read it in very different ways. This implies that expression prediction from t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0d97ee4f406ae4abcb8e15b1461ffdc0
https://doi.org/10.1109/icassp.2014.6854065
https://doi.org/10.1109/icassp.2014.6854065
Autor:
Langzhou Chen, Norbert Braunschweiler
Publikováno v:
INTERSPEECH
This work aims to improve expressive speech synthesis of ebooks for multiple speakers by using training data from many audiobooks. Audiobooks contain a wide variety of expressive speaking styles which are often impractical to annotate. However, the s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a5709a1eed67ffccfa92cec80b9eeb5b
https://doi.org/10.21437/interspeech.2013-115
https://doi.org/10.21437/interspeech.2013-115