Výsledky vyhledávání - "Jiang, Zhongjie"

Report

Lightweight Speaker Verification Using Transformation Module with Feature Partition and Fusion

Autor: Li, Yanxiong, Jiang, Zhongjie, Huang, Qisheng, Cao, Wenchang, Li, Jialong

Although many efforts have been made on decreasing the model complexity for speaker verification, it is still challenging to deploy speaker verification systems with satisfactory result on low-resource terminals. We design a transformation module tha

Externí odkaz: http://arxiv.org/abs/2312.03324

Zobrazit plný text záznamu

Report

Speaker verification using attentive multi-scale convolutional recurrent network

Autor: Li, Yanxiong, Jiang, Zhongjie, Cao, Wenchang, Huang, Qisheng

In this paper, we propose a speaker verification method by an Attentive Multi-scale Convolutional Recurrent Network (AMCRN). The proposed AMCRN can acquire both local spatial information and global sequential information from the input speech recordi

Externí odkaz: http://arxiv.org/abs/2306.00426

Zobrazit plný text záznamu

Akademický článek

Multi-objective optimization in fixed-outline floorplanning with reinforcement learning

Autor: Jiang, Zhongjie, Li, Zhiqiang, Yao, Zhenjie

Publikováno v: In Computers and Electrical Engineering December 2024 120 Part B

Zobrazit plný text záznamu

Report

INTERSPEECH 2021 ConferencingSpeech Challenge: Towards Far-field Multi-Channel Speech Enhancement for Video Conferencing

Autor: Rao, Wei, Fu, Yihui, Hu, Yanxin, Xu, Xin, Jv, Yvkai, Han, Jiangyu, Jiang, Zhongjie, Xie, Lei, Wang, Yannan, Watanabe, Shinji, Tan, Zheng-Hua, Bu, Hui, Yu, Tao, Shang, Shidong

The ConferencingSpeech 2021 challenge is proposed to stimulate research on far-field multi-channel speech enhancement for video conferencing. The challenge consists of two separate tasks: 1) Task 1 is multi-channel speech enhancement with single micr

Externí odkaz: http://arxiv.org/abs/2104.00960

Zobrazit plný text záznamu