Zobrazeno 1 - 10
of 866
pro vyhledávání: '"Shih, P. J."'
Autor:
Badlani, Rohan, Arora, Akshit, Ghosh, Subhankar, Valle, Rafael, Shih, Kevin J., Santos, João Felipe, Ginsburg, Boris, Catanzaro, Bryan
We introduce VANI, a very lightweight multi-lingual accent controllable speech synthesis system. Our model builds upon disentanglement strategies proposed in RADMMM and supports explicit control of accent, language, speaker and fine-grained $F_0$ and
Externí odkaz:
http://arxiv.org/abs/2303.07578
Autor:
Badlani, Rohan, Valle, Rafael, Shih, Kevin J., Santos, João Felipe, Gururani, Siddharth, Catanzaro, Bryan
We work to create a multilingual speech synthesis system which can generate speech with the proper accent while retaining the characteristics of an individual voice. This is challenging to do because it is expensive to obtain bilingual training data
Externí odkaz:
http://arxiv.org/abs/2301.10335
In this paper, we present a novel flow model and compensation strategy for high-viscosity fluid deposition that yields high quality parts in the face of large transient delays and nonlinearity. Robotic high-viscosity fluid deposition is an essential
Externí odkaz:
http://arxiv.org/abs/2210.10747
Human pose transfer synthesizes new view(s) of a person for a given pose. Recent work achieves this via self-reconstruction, which disentangles a person's pose and texture information by breaking the person down into parts, then recombines them for r
Externí odkaz:
http://arxiv.org/abs/2210.01887
Autor:
Qiu Xuan Tan, Nicholas B. Shannon, Weng Khong Lim, Jing Xian Teo, Daniel R. Y. Yap, Sze Min Lek, Joey W. S. Tan, Shih Jia J. Tan, Josephine Hendrikson, Ying Liu, Gillian Ng, Clara Y. L. Chong, Wanyu Guo, Kelvin K. N. Koh, Cedric C. Y. Ng, Vikneswari Rajasegaran, Jolene S.M. Wong, Chin Jin Seo, Choon Kiat Ong, Tony K. H. Lim, Bin Tean Teh, Oi Lian Kon, Claramae S. Chia, Khee Chee Soo, N. Gopalakrishna Iyer, Chin-Ann J. Ong
Publikováno v:
Frontiers in Oncology, Vol 14 (2024)
IntroductionField cancerization is suggested to arise from imbalanced differentiation in individual basal progenitor cells leading to clonal expansion of mutant cells that eventually replace the epithelium, although without evidence.MethodsWe perform
Externí odkaz:
https://doaj.org/article/281912497fc44f628bdcedeb2a207a97
Despite recent advances in generative modeling for text-to-speech synthesis, these models do not yet have the same fine-grained adjustability of pitch-conditioned deterministic models such as FastPitch and FastSpeech2. Pitch information is not only l
Externí odkaz:
http://arxiv.org/abs/2203.01786
Speech-to-text alignment is a critical component of neural textto-speech (TTS) models. Autoregressive TTS models typically use an attention mechanism to learn these alignments on-line. However, these alignments tend to be brittle and often fail to ge
Externí odkaz:
http://arxiv.org/abs/2108.10447
Publikováno v:
Frontiers in Molecular Neuroscience, Vol 16 (2024)
Alzheimer’s disease (AD) is characterized by a long preclinical phase. Although late-stage AD/dementia may be robustly differentiated from cognitively normal individuals by means of a clinical evaluation, PET imaging, and established biofluid bioma
Externí odkaz:
https://doaj.org/article/3ebe80f4674d462386cdd1e5b77ef3fc
Autor:
Dundar, Aysegul, Shih, Kevin J., Garg, Animesh, Pottorf, Robert, Tao, Andrew, Catanzaro, Bryan
Unsupervised landmark learning is the task of learning semantic keypoint-like representations without the use of expensive input keypoint-level annotations. A popular approach is to factorize an image into a pose and appearance data stream, then to r
Externí odkaz:
http://arxiv.org/abs/2001.09518
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.