Zobrazeno 1 - 10
of 483
pro vyhledávání: '"Shugong Xu"'
Publikováno v:
EURASIP Journal on Audio, Speech, and Music Processing, Vol 2024, Iss 1, Pp 1-18 (2024)
Abstract In the era of advanced text-to-speech (TTS) systems capable of generating high-fidelity, human-like speech by referring a reference speech, voice cloning (VC), or zero-shot TTS (ZS-TTS), stands out as an important subtask. A primary challeng
Externí odkaz:
https://doaj.org/article/e08805403ca34028a8d742b9a22ab0cc
Autor:
Zhiyong Chen, Shugong Xu
Publikováno v:
EURASIP Journal on Audio, Speech, and Music Processing, Vol 2023, Iss 1, Pp 1-17 (2023)
Abstract Speaker recognition, the process of automatically identifying a speaker based on individual characteristics in speech signals, presents significant challenges when addressing heterogeneous-domain conditions. Federated learning, a recent deve
Externí odkaz:
https://doaj.org/article/ce507c02ff854c68a668b34eebb84c3b
Publikováno v:
IEEE Access, Vol 11, Pp 58808-58821 (2023)
Image matting is an important computer vision problem. Many existing matting methods leverage a hand-made trimap to provide auxiliary information, which is expensive and time-consuming for real-world applications. In recent years, some trimap-free me
Externí odkaz:
https://doaj.org/article/e25c9d3e04e143b8aead1ff38d6290e4
Publikováno v:
IEEE Access, Vol 11, Pp 47608-47618 (2023)
Human age information is present in the face image and speech, but most age estimation methods focus on single-modal data only. Although multi-modal approaches have achieved promising performance in other fields by leveraging complementarity between
Externí odkaz:
https://doaj.org/article/896fe7f5fe1f4288a5869b6014c24c3c
Autor:
Qiuyue Liao, Qi Zhang, Xue Feng, Haibo Huang, Haohao Xu, Baoyuan Tian, Jihao Liu, Qihui Yu, Na Guo, Qun Liu, Bo Huang, Ding Ma, Jihui Ai, Shugong Xu, Kezhen Li
Publikováno v:
Communications Biology, Vol 4, Iss 1, Pp 1-9 (2021)
Liao et al. propose a deep learning model to predict blastocyst formation using TLM videos following the first three days of embryogenesis. The authors develop an ensemble prediction model, STEM and STEM+, which were found to exhibit 78.2% and 71.9%
Externí odkaz:
https://doaj.org/article/22365fca6617491f82115a898e8b8c2e
Publikováno v:
IEEE Access, Vol 9, Pp 28140-28155 (2021)
Face Anti-spoofing (FAS) is a challenging problem due to complex serving scenarios and diverse face presentation attack patterns. Especially when captured images are low-resolution, blurry, and coming from different domains, the performance of FAS wi
Externí odkaz:
https://doaj.org/article/35784957152c4b5db1c2c29468b477b6
Publikováno v:
IEEE Access, Vol 9, Pp 46325-46338 (2021)
Recently, video scene text detection has received increasing attention due to its comprehensive applications. However, the lack of annotated scene text video datasets has become one of the most important problems, which hinders the development of vid
Externí odkaz:
https://doaj.org/article/b1f7df94a49440c2bd6ebd850409abbd
Publikováno v:
IEEE Access, Vol 9, Pp 61369-61382 (2021)
Beyond the underlaying unrealistic presumptions in the existing video deblurring datasets and algorithms which presume that a naturally blurred video is fully blurred. In this work, we define a more realistic video frames averaging-based data degrada
Externí odkaz:
https://doaj.org/article/d0142db6cd0b49ea950558332f9852ee
Publikováno v:
IEEE Access, Vol 9, Pp 65162-65172 (2021)
Dual connectivity (DC) is a key technology to improve the throughput of the fifth generation communication networks (5G) system. Due to the limitation of the splitting strategy and transmission delay of different transmission nodes, the out-of-order
Externí odkaz:
https://doaj.org/article/e0bb4235536b4ffd9f08f3ca81b67c33
Publikováno v:
IEEE Access, Vol 9, Pp 158481-158495 (2021)
The emergence of Mobile Edge Computing (MEC) provides a near-field tasking platform to meet the latency requirements of the growing number of compute-intensive mobile applications. However, physical memory constraints limit the number of application
Externí odkaz:
https://doaj.org/article/0ec1d7854b2e44a890548e3deb1e39c9