Zobrazeno 1 - 10
of 861
pro vyhledávání: '"Yan Yonghong"'
Publikováno v:
Redai dili, Vol 44, Iss 2, Pp 280-291 (2024)
The transformation and reconstruction of traditional villages into "post-rural" tourism communities constitute a primary pathway for achieving modernization in rural areas on the outskirts of large metropolitan areas and advancing countryside revital
Externí odkaz:
https://doaj.org/article/6c6d94c51c60406893fe0c585fad13b3
Speech enhancement is designed to enhance the intelligibility and quality of speech across diverse noise conditions. Recently, diffusion model has gained lots of attention in speech enhancement area, achieving competitive results. Current diffusion-b
Externí odkaz:
http://arxiv.org/abs/2409.15101
This paper presents an approach to authoring a textbook titled Interactive OpenMP Programming with the assistance of Large Language Models (LLMs). The writing process utilized state-of-the-art LLMs, including Gemini Pro 1.5, Claude 3, and ChatGPT-4,
Externí odkaz:
http://arxiv.org/abs/2409.09296
In multi-agent cooperative tasks, the presence of heterogeneous agents is familiar. Compared to cooperation among homogeneous agents, collaboration requires considering the best-suited sub-tasks for each agent. However, the operation of multi-agent s
Externí odkaz:
http://arxiv.org/abs/2408.07098
When labeled data is insufficient, semi-supervised learning with the pseudo-labeling technique can significantly improve the performance of automatic speech recognition. However, pseudo-labels are often noisy, containing numerous incorrect tokens. Ta
Externí odkaz:
http://arxiv.org/abs/2308.06547
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing, Volume 28, 2020, Pages 1452 - 1465
Recently, there has been increasing progress in end-to-end automatic speech recognition (ASR) architecture, which transcribes speech to text without any pre-trained alignments. One popular end-to-end approach is the hybrid Connectionist Temporal Clas
Externí odkaz:
http://arxiv.org/abs/2307.02351
Previous research in speech enhancement has mostly focused on modeling time or time-frequency domain information alone, with little consideration given to the potential benefits of simultaneously modeling both domains. Since these domains contain com
Externí odkaz:
http://arxiv.org/abs/2305.08292
Selecting application scenarios matching data is important for the automatic speech recognition (ASR) training, but it is difficult to measure the matching degree of the training corpus. This study proposes a unsupervised target-aware data selection
Externí odkaz:
http://arxiv.org/abs/2302.13222
Publikováno v:
Journal of Applied Physics; 9/28/2024, Vol. 136 Issue 12, p1-10, 10p
Autor:
Deng, Shuhao, Li, Chengfei, Bai, Jinfeng, Zhang, Qingqing, Zhang, Wei-Qiang, Yang, Runyan, Cheng, Gaofeng, Zhang, Pengyuan, Yan, Yonghong
Code-switching automatic speech recognition becomes one of the most challenging and the most valuable scenarios of automatic speech recognition, due to the code-switching phenomenon between multilingual language and the frequent occurrence of code-sw
Externí odkaz:
http://arxiv.org/abs/2210.06091