Zobrazeno 1 - 10
of 245
pro vyhledávání: '"Jiao, Yunlong"'
Autor:
Feng, Yue, Jiao, Yunlong, Prasad, Animesh, Aletras, Nikolaos, Yilmaz, Emine, Kazai, Gabriella
User Satisfaction Modeling (USM) is one of the popular choices for task-oriented dialogue systems evaluation, where user satisfaction typically depends on whether the user's task goals were fulfilled by the system. Task-oriented dialogue systems use
Externí odkaz:
http://arxiv.org/abs/2305.16798
Autor:
Shi, Zhengxiang, Tonolini, Francesco, Aletras, Nikolaos, Yilmaz, Emine, Kazai, Gabriella, Jiao, Yunlong
Semi-supervised learning (SSL) is a popular setting aiming to effectively utilize unlabelled data to improve model performance in downstream natural language processing (NLP) tasks. Currently, there are two popular approaches to make use of unlabelle
Externí odkaz:
http://arxiv.org/abs/2305.13002
Advances in deep learning theory have revealed how average generalization relies on superficial patterns in data. The consequences are brittle models with poor performance with shift in group distribution at test time. When group annotation is availa
Externí odkaz:
http://arxiv.org/abs/2210.12195
Autor:
Jiao, Yunlong, He, Ding, Zhang, Shuya, Cheng, Mengzhu, Chen, Si, Dong, Tinglan, Wang, Lihong, Huang, Xiaohua
Publikováno v:
In Ecotoxicology and Environmental Safety August 2024 281
Acquiring accurate labels on large-scale datasets is both time consuming and expensive. To reduce the dependency of deep learning models on learning from clean labeled data, several recent research efforts are focused on learning with noisy labels. T
Externí odkaz:
http://arxiv.org/abs/2201.10836
In NLP, a large volume of tasks involve pairwise comparison between two sequences (e.g. sentence similarity and paraphrase identification). Predominantly, two formulations are used for sentence-pair tasks: bi-encoders and cross-encoders. Bi-encoders
Externí odkaz:
http://arxiv.org/abs/2109.13059
Publikováno v:
In Journal of Controlled Release July 2024 371:516-529
This paper proposes a general enhancement to the Normalizing Flows (NF) used in neural vocoding. As a case study, we improve expressive speech vocoding with a revamped Parallel Wavenet (PW). Specifically, we propose to extend the affine transformatio
Externí odkaz:
http://arxiv.org/abs/2106.08649
Autor:
Guo, Yuhang, Liu, Xiaojun, Ji, Jiawei, Wang, Zhaochang, Hu, Xidong, Zhu, Yongqing, Wang, Jiaxiang, Du, Yu, Liu, Kun, Jiao, Yunlong
Publikováno v:
In Applied Thermal Engineering 1 April 2024 242
Autor:
Jiao, Yunlong, Gabrys, Adam, Tinchev, Georgi, Putrycz, Bartosz, Korzekwa, Daniel, Klimkov, Viacheslav
We present a universal neural vocoder based on Parallel WaveNet, with an additional conditioning network called Audio Encoder. Our universal vocoder offers real-time high-quality speech synthesis on a wide range of use cases. We tested it on 43 inter
Externí odkaz:
http://arxiv.org/abs/2102.01106