|
|
|
|
|
Jinn-Chyi Chen, Xun-Rui Fan, Jian-Qiang Fan, Xi-Zhu Lai, Gui-Liang Li and Feng-Bin Li
This study investigated the visual harmony of an urban stream considering changes to the ratio of water to greenery on the riverbed. The Baxi stream, a third-order stream in Yongan City, Fujian Province, China was selected as the study site. The stream r...
ver más
|
|
|
|
|
|
|
|
|
|
|
Jiachen Zhang, Guoqing Tu, Shubo Liu and Zhaohui Cai
The rapid development of speech synthesis technology has significantly improved the naturalness and human-likeness of synthetic speech. As the technical barriers for speech synthesis are rapidly lowering, the number of illegal activities such as fraud an...
ver más
|
|
|
|
|
|
|
|
|
|
|
Jialin Zhang, Mairidan Wushouer, Gulanbaier Tuerhong and Hanfang Wang
Emotional speech synthesis is an important branch of human?computer interaction technology that aims to generate emotionally expressive and comprehensible speech based on the input text. With the rapid development of speech synthesis technology based on ...
ver más
|
|
|
|
|
|
|
|
|
|
|
Kadria Ezzine, Joseph Di Martino and Mondher Frikha
We present an any-to-one voice conversion (VC) system, using an autoregressive model and LPCNet vocoder, aimed at enhancing the converted speech in terms of naturalness, intelligibility, and speaker similarity. As the name implies, non-parallel any-to-on...
ver más
|
|
|
|
|
|
|
|
|
|
|
Víctor García, Inma Hernáez and Eva Navas
In this paper, we describe the implementation and evaluation of Text to Speech synthesizers based on neural networks for Spanish and Basque. Several voices were built, all of them using a limited number of data. The system applies Tacotron 2 to compute m...
ver más
|
|
|
|
|
|
|
|
|
|
|
Ki-Seung Lee
Moderate performance in terms of intelligibility and naturalness can be obtained using previously established silent speech interface (SSI) methods. Nevertheless, a common problem associated with SSI has involved deficiencies in estimating the spectrum d...
ver más
|
|
|
|
|
|
|
|
|
|
|
Vladimir Kurcubic, Slavi?a Stajic, Nemanja Miletic and Nikola Stani?ic
Meat manufacturers are nowadays in a very unenviable position. Both meat and meat products require the utilization of various additives due to their chemical composition. On the other hand, consumers demand fresh, additive-free, and high-quality products...
ver más
|
|
|
|
|
|
|
|
|
|
|
Shahida Anusha Siddiqui, Sipper Khan, Misbah Murid, Zarnab Asif, Natalya Pavlovna Oboturova, Andrey Ashotovich Nagdalian, Andrey Vladimirovich Blinov, Salam A. Ibrahim and Seid Mahdi Jafari
Environmentally intense and negative consequences relateing to conventional meat production systems have induced some actors to suggest alternative meat sources. Diseases carried by animals, human perception of cruelty to animals, and public health conce...
ver más
|
|
|
|
|
|
|
|
|
|
|
Fei Wang, Lu Leng, Andrew Beng Jin Teoh and Jun Chu
Biometric-based authentication is widely deployed on multimedia systems currently; however, biometric systems are vulnerable to image-level attacks for impersonation. Reconstruction attack (RA) and presentation attack (PA) are two typical instances for i...
ver más
|
|
|
|
|
|
|
|
|
|
|
Sung Jun Cheon, Joun Yeop Lee, Byoung Jin Choi, Hyeonseung Lee and Nam Soo Kim
End-to-end neural network-based speech synthesis techniques have been developed to represent and synthesize speech in various prosodic style. Although the end-to-end techniques enable the transfer of a style with a single vector of style representation, ...
ver más
|
|
|
|
|
|