Zobrazeno 1 - 10
of 132
pro vyhledávání: '"Chung-Cheng Chiu"'
Publikováno v:
Applied Sciences, Vol 12, Iss 13, p 6602 (2022)
Object segmentation and object labeling are important techniques in the field of image processing. Because object segmentation techniques developed using two-dimensional images may cause segmentation errors for overlapping objects, this paper propose
Externí odkaz:
https://doaj.org/article/b2f472cd7ede451a9713cfd2c6adf449
Publikováno v:
IEEE Access, Vol 5, Pp 22992-23009 (2017)
The skyline is a piece of important reference information in the automatic flight control system of an unmanned vehicle. Currently, most skyline detection algorithms assume that the skyline has distinct edge features that can be located in the image
Externí odkaz:
https://doaj.org/article/d76fcbce35594431886b61dbbe24285d
Publikováno v:
Sensors, Vol 15, Iss 9, Pp 23763-23787 (2015)
In this paper, we propose a fast labeling algorithm based on block-based concepts. Because the number of memory access points directly affects the time consumption of the labeling algorithms, the aim of the proposed algorithm is to minimize neighborh
Externí odkaz:
https://doaj.org/article/e8c7f2ccf4424e118db152f2bea1c9d7
Publikováno v:
Sensors, Vol 15, Iss 7, Pp 16981-16999 (2015)
Image enhancement techniques primarily improve the contrast of an image to lend it a better appearance. One of the popular enhancement methods is histogram equalization (HE) because of its simplicity and effectiveness. However, it is rarely applied t
Externí odkaz:
https://doaj.org/article/0a5ae127195243d3b3efdf9571775e26
Publikováno v:
Sensors, Vol 15, Iss 7, Pp 16848-16865 (2015)
The fastest and most economical method of acquiring terrain images is aerial photography. The use of unmanned aerial vehicles (UAVs) has been investigated for this task. However, UAVs present a range of challenges such as flight altitude maintenance.
Externí odkaz:
https://doaj.org/article/010662d1ffba4f9ca9e873f042b0cac4
Autor:
Shou-Cih Chen, Chung-Cheng Chiu
Publikováno v:
Applied Sciences, Vol 9, Iss 5, p 897 (2019)
The edge detection algorithm is the cornerstone of image processing; a good edge detection result can further extract the required information through rich texture information and achieve object detection, segmentation, and identification. To obtain
Externí odkaz:
https://doaj.org/article/82d7a15d3cf44c21ab81948347177ce0
Publikováno v:
Applied Sciences, Vol 8, Iss 6, p 885 (2018)
Background subtraction is a mainstream algorithm for moving object detection in video surveillance systems. It segments moving objects by using the difference between the background and input images. The key to background subtraction is to establish
Externí odkaz:
https://doaj.org/article/688b3999feb44caca1b4f2d35ab7c6df
Autor:
Yu Zhang, Daniel S. Park, Wei Han, James Qin, Anmol Gulati, Joel Shor, Aren Jansen, Yuanzhong Xu, Yanping Huang, Shibo Wang, Zongwei Zhou, Bo Li, Min Ma, William Chan, Jiahui Yu, Yongqiang Wang, Liangliang Cao, Khe Chai Sim, Bhuvana Ramabhadran, Tara N. Sainath, Francoise Beaufays, Zhifeng Chen, Quoc V. Le, Chung-Cheng Chiu, Ruoming Pang, Yonghui Wu
We summarize the results of a host of efforts using giant automatic speech recognition (ASR) models pre-trained using large, diverse unlabeled datasets containing approximately a million hours of audio. We find that the combination of pre-training, s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7dea4e39aabfa465900cf742628eef2c
http://arxiv.org/abs/2109.13226
http://arxiv.org/abs/2109.13226
Publikováno v:
Interspeech 2021.
We combine recent advancements in end-to-end speech recognition to non-autoregressive automatic speech recognition. We push the limits of non-autoregressive state-of-the-art results for multiple datasets: LibriSpeech, Fisher+Switchboard and Wall Stre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::24c69b8641ff720072a2c5bc14d8ad0b
https://doi.org/10.21437/interspeech.2021-337
https://doi.org/10.21437/interspeech.2021-337
Autor:
Wei Han, Tara N. Sainath, Bo Li, Yonghui Wu, Anmol Gulati, Arun Narayanan, Ruoming Pang, Shuo-Yiin Chang, Chung-Cheng Chiu, Yanzhang He, Jiahui Yu
Publikováno v:
ICASSP
Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible. However, emitting fast without degrading quality, as measured by word error rate (WER), is highly challenging. Existing approaches
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9136dd1ce22ab5c87c1875fef2f8b399
https://doi.org/10.1109/icassp39728.2021.9413803
https://doi.org/10.1109/icassp39728.2021.9413803