Zobrazeno 1 - 10
of 602
pro vyhledávání: '"Yang Yudong"'
Stuttering is a neurodevelopmental speech disorder characterized by common speech symptoms such as pauses, exclamations, repetition, and prolongation. Speech-language pathologists typically assess the type and severity of stuttering by observing thes
Externí odkaz:
http://arxiv.org/abs/2411.09479
Autor:
Tang, Changli, Li, Yixuan, Yang, Yudong, Zhuang, Jimin, Sun, Guangzhi, Li, Wei, Ma, Zujun, Zhang, Chao
Videos contain a wealth of information, and generating detailed and accurate descriptions in natural language is a key aspect of video understanding. In this paper, we present video-SALMONN 2, an advanced audio-visual large language model (LLM) with
Externí odkaz:
http://arxiv.org/abs/2410.06682
Autor:
Wang, Siyin, Yu, Wenyi, Yang, Yudong, Tang, Changli, Li, Yixuan, Zhuang, Jimin, Chen, Xianzhao, Tian, Xiaohai, Zhang, Jun, Sun, Guangzhi, Lu, Lu, Zhang, Chao
Speech quality assessment typically requires evaluating audio from multiple aspects, such as mean opinion score (MOS) and speaker similarity (SIM) etc., which can be challenging to cover using one small model designed for a single task. In this paper
Externí odkaz:
http://arxiv.org/abs/2409.16644
Diffusion-based generative models have recently achieved remarkable results in speech and vocal enhancement due to their ability to model complex speech data distributions. While these models generalize well to unseen acoustic environments, they may
Externí odkaz:
http://arxiv.org/abs/2409.09642
The field of evolutionary many-task optimization (EMaTO) is increasingly recognized for its ability to streamline the resolution of optimization challenges with repetitive characteristics, thereby conserving computational resources. This paper tackle
Externí odkaz:
http://arxiv.org/abs/2407.08918
Autor:
Liu, Xiaokang, Du, Xiaoxia, Liu, Juan, Su, Rongfeng, Ng, Manwa Lawrence, Zhang, Yumei, Yang, Yudong, Zhao, Shaofeng, Wang, Lan, Yan, Nan
Automatic assessment of dysarthria remains a highly challenging task due to high variability in acoustic signals and the limited data. Currently, research on the automatic assessment of dysarthria primarily focuses on two approaches: one that utilize
Externí odkaz:
http://arxiv.org/abs/2405.03254
Acoustic-to-articulatory inversion (AAI) is to convert audio into articulator movements, such as ultrasound tongue imaging (UTI) data. An issue of existing AAI methods is only using the personalized acoustic information to derive the general patterns
Externí odkaz:
http://arxiv.org/abs/2403.05820
Autor:
Klemke Nicolai, Tancogne-Dejean Nicolas, Rossi Giulio M., Yang Yudong, Mainz Roland E., Di Sciacca Giuseppe, Rubio Angel, Kärtner Franz X., Mücke Oliver D.
Publikováno v:
EPJ Web of Conferences, Vol 205, p 02022 (2019)
The polarization states of high-harmonics generated in silicon with elliptical excitation are studies. Circularly polarized harmonics are demonstrated with both circular and non-circular excitation, determined by crystal symmetry and the dynamical re
Externí odkaz:
https://doaj.org/article/c5161d96139a4a5a873ce468b031dcb9
Autor:
Scheiba Fabian, Rossi Giulio Maria, Mainz Roland E., Yang Yudong, Cirmi Giovanni, Kärtner Franz X.
Publikováno v:
EPJ Web of Conferences, Vol 205, p 01011 (2019)
We report on an optical synthesis of two compressed channels from our parametric waveform synthesizer, leading to a 0.6 mJ 3.4 fs pulse (3.2 fs transform limited) with a central wavelength of 1.8 /an, corresponding to 0.6 optical cycles.
Externí odkaz:
https://doaj.org/article/8c623ee95034435a8b2ba69e254bcbcd
Publikováno v:
International Journal of Emerging Markets, 2022, Vol. 19, Issue 7, pp. 1981-2002.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/IJOEM-03-2022-0456