Zobrazeno 1 - 10
of 4 459
pro vyhledávání: '"Hsu, Ming"'
This paper presents Meta-Whisper, a novel approach to improve automatic speech recognition (ASR) for low-resource languages using the Whisper model. By leveraging Meta In-Context Learning (Meta-ICL) and a k-Nearest Neighbors (KNN) algorithm for sampl
Externí odkaz:
http://arxiv.org/abs/2409.10429
Autor:
Shih, Min-Han, Chung, Ho-Lam, Pai, Yu-Chi, Hsu, Ming-Hao, Lin, Guan-Ting, Li, Shang-Wen, Lee, Hung-yi
Publikováno v:
Proc. Interspeech 2024, 2970-2974
In recent advancements in spoken question answering (QA), end-to-end models have made significant strides. However, previous research has primarily focused on extractive span selection. While this extractive-based approach is effective when answers a
Externí odkaz:
http://arxiv.org/abs/2312.09781
Ever since the development of GPT-3 in the natural language processing (NLP) field, in-context learning (ICL) has played an essential role in utilizing large language models (LLMs). By presenting the LM utterance-label demonstrations at the input, th
Externí odkaz:
http://arxiv.org/abs/2310.12477
In this report, we demonstrate that Ge-NWQD (nanowire quantum dots) at low temperatures exhibit apparent Coulomb oscillations than that in Si-NWQD. These oscillations gradually disappear as the temperature increases, indicating the influence of phono
Externí odkaz:
http://arxiv.org/abs/2307.05342
Imitation learning addresses the challenge of learning by observing an expert's demonstrations without access to reward signals from environments. Most existing imitation learning methods that do not require interacting with environments either model
Externí odkaz:
http://arxiv.org/abs/2302.13335
Direct Immersogeometric Fluid Flow and Heat Transfer Analysis of Objects Represented by Point Clouds
Autor:
Balu, Aditya, Rajanna, Manoj R., Khristy, Joel, Xu, Fei, Krishnamurthy, Adarsh, Hsu, Ming-Chen
Immersogeometric analysis (IMGA) is a geometrically flexible method that enables one to perform multiphysics analysis directly using complex computer-aided design (CAD) models. In this paper, we develop a novel IMGA approach for simulating incompress
Externí odkaz:
http://arxiv.org/abs/2210.13737
The recovery of an unknown density matrix of large size requires huge computational resources. The recent Factored Gradient Descent (FGD) algorithm and its variants achieved state-of-the-art performance since they could mitigate the dimensionality ba
Externí odkaz:
http://arxiv.org/abs/2210.04717