Search Results - "Xia, Shipeng"

The XMUSPEECH System for Accented English Automatic Speech Recognition by Tong, Fuchuan, Li, Tao, Liao, Dexin, Xia, Shipeng, Li, Song, Hong, Qingyang, Li, Lin

“…In this paper, we present the XMUSPEECH systems for Track 2 of the Interspeech 2020 Accented English Speech Recognition Challenge (AESRC2020). Track 2 is an…”
Get full text

End-To-End Multi-Accent Speech Recognition with Unsupervised Accent Modelling by Li, Song, Ouyang, Beibei, Liao, Dexin, Xia, Shipeng, Li, Lin, Hong, Qingyang

“…End-to-end speech recognition has achieved good recognition performance on standard English pronunciation datasets. However, one prominent problem with…”
Get full text

Rapid Springback Compensation for Age Forming Based on Quasi Newton Method by Xiong, Wei, Gan, Zhong, Xiong, Shipeng, Xia, Yushan

“…Iterative methods based on finite element simulation are effective approaches to design mold shape to compensate springback in sheet metal forming. However,…”
Get full text

Spatial-aware Speaker Diarization for Multi-channel Multi-party Meeting by Wang, Jie, Liu, Yuji, Wang, Binling, Zhi, Yiming, Li, Song, Xia, Shipeng, Zhang, Jiayang, Tong, Feng, Li, Lin, Hong, Qingyang

“…This paper describes a spatial-aware speaker diarization system for the multi-channel multi-party meeting. The diarization system obtains direction information…”
Get full text

The xmuspeech system for multi-channel multi-party meeting transcription challenge by Wang, Jie, Liu, Yuji, Wang, Binling, Zhi, Yiming, Li1, Song, Xia, Shipeng, Zhang, Jiayang, Li1, Lin, Hong, Qingyang, Tong, Feng

“…This paper describes the system developed by the XMUSPEECH team for the Multi-channel Multi-party Meeting Transcription Challenge (M2MeT). For the speaker…”
Get full text

Phone-Aware Multi-task Learning and Length Expanding for Short-Duration Language Recognition by Zhao, Miao, Li, Rongjin, Yan, Shijiang, Li, Zheng, Lu, Hao, Xia, Shipeng, Hong, Qingyang, Li, Lin

“…In the language recognition, the phonetic information has shown great potential for neural network to learn the high-level representations. In this paper, we…”
Get full text