Zobrazeno 1 - 10
of 729
pro vyhledávání: '"Da Rong"'
Autor:
Cheng, Da Rong
We extend Struwe's result (Acta Math., 1988) on the existence of free boundary constant mean curvature disks to almost every prescribed boundary contact angle in $(0, \pi)$. Specifically, let $\Sigma$ be a surface in $\mathbb{R}^3$ diffeomorphic to t
Externí odkaz:
http://arxiv.org/abs/2310.08300
Autor:
Liu, Da-rong, Hsu, Po-chun, Chen, Yi-chen, Huang, Sung-feng, Chuang, Shun-po, Wu, Da-yi, Lee, Hung-yi
ASR has been shown to achieve great performance recently. However, most of them rely on massive paired data, which is not feasible for low-resource languages worldwide. This paper investigates how to learn directly from unpaired phone sequences and s
Externí odkaz:
http://arxiv.org/abs/2207.14568
Autoregressive neural vocoders have achieved outstanding performance in speech synthesis tasks such as text-to-speech and voice conversion. An autoregressive vocoder predicts a sample at some time step conditioned on those at previous time steps. Tho
Externí odkaz:
http://arxiv.org/abs/2204.11806
Publikováno v:
Calculus of Variations and Partial Differential Equations 62 (2023), 174, 38pp
Let $M$ be a fixed compact oriented embedded submanifold of a manifold $\overline{M}$. Consider the volume $\mathcal{V} (\overline{g}) = \int_M \mathsf{vol}_{(M, g)}$ as a functional of the ambient metric $\overline{g}$ on $\overline{M}$, where $g =
Externí odkaz:
http://arxiv.org/abs/2204.08591
Publikováno v:
ZooKeys, Vol 1190, Iss , Pp 91-106 (2024)
The adult, pupa and larva of a new species, Gnaptorina (Gnaptorina) lhorongica Li, sp. nov., from northeastern Xizang, China are described and illustrated. The species was identified using molecular phylogenetic analyses based on three mitochondrial
Externí odkaz:
https://doaj.org/article/3dd07a0b91814d649de407505466be63
Universal Adaptor: Converting Mel-Spectrograms Between Different Configurations for Speech Synthesis
Most recent speech synthesis systems are composed of a synthesizer and a vocoder. However, the existing synthesizers and vocoders can only be matched to acoustic features extracted with a specific configuration. Hence, we can't combine arbitrary synt
Externí odkaz:
http://arxiv.org/abs/2204.00170
Autor:
Cheng, Da Rong
Given a surface $\Sigma$ in $\mathbb{R}^3$ diffeomorphic to $S^2$, Struwe (Acta Math., 1988) proved that for almost every $H$ below the mean curvature of the smallest sphere enclosing $\Sigma$, there exists a branched immersed disk which has constant
Externí odkaz:
http://arxiv.org/abs/2203.16323
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 30, pp. 1558-1571, 2022
Personalizing a speech synthesis system is a highly desired application, where the system can generate speech with the user's voice with rare enrolled recordings. There are two main approaches to build such a system in recent works: speaker adaptatio
Externí odkaz:
http://arxiv.org/abs/2111.04040
Unsupervised speech recognition (unsupervised ASR) aims to learn the ASR system with non-parallel speech and text corpus only. Wav2vec-U has shown promising results in unsupervised ASR by self-supervised speech representations coupled with Generative
Externí odkaz:
http://arxiv.org/abs/2110.03509