Výsledky vyhledávání

This paper introduces F5-TTS, a fully non-autoregressive text-to-speech system based on flow matching with Diffusion Transformer (DiT). Without requiring complex designs such as duration model, text encoder, and phoneme alignment, the text input is s

Externí odkaz: http://arxiv.org/abs/2410.06885

Zobrazit plný text záznamu

Report

CoT-ST: Enhancing LLM-based Speech Translation with Multimodal Chain-of-Thought

Autor: Du, Yexing, Ma, Ziyang, Yang, Yifan, Deng, Keqi, Chen, Xie, Yang, Bo, Xiang, Yang, Liu, Ming, Qin, Bing

Speech Language Models (SLMs) have demonstrated impressive performance on speech translation tasks. However, existing research primarily focuses on direct instruction fine-tuning and often overlooks the inherent reasoning capabilities of SLMs. In thi

Externí odkaz: http://arxiv.org/abs/2409.19510

Zobrazit plný text záznamu

Report

Nodeless superconductivity and topological nodal states in molybdenum carbide

Autor: Shang, Tian, Wang, Yuting, Yu, Bochen, Xia, Keqi, Gawryluk, Darek J., Xu, Yang, Zhan, Qingfeng, Zhao, Jianzhou, Shiroka, Toni

Publikováno v: Phys. Rev. B. 110, 064510 (2024)

The orthorhombic molybdenum carbide superconductor with $T_c$ = 3.2 K was investigated by muon-spin rotation and relaxation ($\mu$SR) measurements and by first-principle calculations. The low-temperature superfluid density, determined by transverse-f

Externí odkaz: http://arxiv.org/abs/2409.02380

Zobrazit plný text záznamu

Report

Label-Synchronous Neural Transducer for E2E Simultaneous Speech Translation

Autor: Deng, Keqi, Woodland, Philip C.

While the neural transducer is popular for online speech recognition, simultaneous speech translation (SST) requires both streaming and re-ordering capabilities. This paper presents the LS-Transducer-SST, a label-synchronous neural transducer for SST

Externí odkaz: http://arxiv.org/abs/2406.04541

Zobrazit plný text záznamu

Report

Wav2Prompt: End-to-End Speech Prompt Generation and Tuning For LLM in Zero and Few-shot Learning

Autor: Deng, Keqi, Sun, Guangzhi, Woodland, Philip C.

Wav2Prompt is proposed which allows straightforward integration between spoken input and a text-based large language model (LLM). Wav2Prompt uses a simple training process with only the same data used to train an automatic speech recognition (ASR) mo

Externí odkaz: http://arxiv.org/abs/2406.00522

Zobrazit plný text záznamu

Report

Charge Collection Performance of 4H-SiC LGAD

Autor: Zhao, Sen, Wang, Keqi, Xie, Kaibo, Fu, Chenxi, Wang, Chengwei, Shi, Xin, Wang, Congcong

The 4H-SiC material exhibits good detection performance, but there are still many problems like signal distortion and poor signal quality. The 4H-SiC low gain avalanche detector (LGAD) has been fabricated for the first time to solve these problems, w

Externí odkaz: http://arxiv.org/abs/2405.18112

Zobrazit plný text záznamu

Report

The Stiffness of 3-PRS PM Across Parasitic and Orientational Workspace

Autor: Nigatu, Hassen, Jihao, Li, Zhu, Keqi, Zhang, Junhan, Guo, Haotian, Lu, Guodong, Kim, Doik

This study investigates the stiffness characteristics of the Sprint Z3 head, also known as 3-PRS Parallel Kinematics Machines, which are among the most extensively researched and viably successful manipulators for precision machining applications. De

Externí odkaz: http://arxiv.org/abs/2405.08418

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání