Search Results - "Gu, Rongzhi"

The Sound Demixing Challenge 2023 – Cinematic Demixing Track by Uhlich, Stefan, Fabbro, Giorgio, Hirano, Masato, Takahashi, Shusuke, Wichern, Gordon, Le Roux, Jonathan, Chakraborty, Dipam, Mohanty, Sharada, Li, Kai, Luo, Yi, Yu, Jianwei, Gu, Rongzhi, Solovyev, Roman, Stempkovskiy, Alexander, Habruseva, Tatiana, Sukhovei, Mikhail, Mitsufuji, Yuki

“…This paper summarizes the cinematic demixing (CDX) track of the Sound Demixing Challenge 2023 (SDX’23). We provide a comprehensive summary of the challenge…”
Get full text

ReZero: Region-Customizable Sound Extraction by Gu, Rongzhi, Luo, Yi

“…We introduce region-customizable sound extraction (ReZero), a general and flexible framework for the multi-channel region-wise sound extraction (R-SE) task…”
Get full text

Improving Music Source Separation with Simo Stereo Band-Split Rnn by Luo, Yi, Gu, Rongzhi

“…With the recent developments of novel neural network designs, the state-of-the-art of music source separation systems has been significantly advanced. For…”
Get full text

Multi-Modal Multi-Channel Target Speech Separation by Gu, Rongzhi, Zhang, Shi-Xiong, Xu, Yong, Chen, Lianwu, Zou, Yuexian, Yu, Dong

“…Target speech separation refers to extracting a target speaker's voice from an overlapped audio of simultaneous talkers. Previously the use of visual modality…”
Get full text

Complex Neural Spatial Filter: Enhancing Multi-Channel Target Speech Separation in Complex Domain by Gu, Rongzhi, Zhang, Shi-Xiong, Zou, Yuexian, Yu, Dong

“…To date, mainstream target speech separation (TSS) approaches are formulated to estimate the complex ratio mask (cRM) of target speech in time-frequency domain…”
Get full text

Improving Dual-Microphone Speech Enhancement by Learning Cross-Channel Features with Multi-Head Attention by Xu, Xinmeng, Gu, Rongzhi, Zou, Yuexian

“…Hand-crafted spatial features, such as inter-channel intensity difference (IID) and inter-channel phase difference (IPD), play a fundamental role in recent…”
Get full text

Enhancing End-to-End Multi-Channel Speech Separation Via Spatial Feature Learning by Gu, Rongzhi, Zhang, Shi-Xiong, Chen, Lianwu, Xu, Yong, Yu, Meng, Su, Dan, Zou, Yuexian, Yu, Dong

“…Hand-crafted spatial features (e.g., inter-channel phase difference, IPD) play a fundamental role in recent deep learning based multi-channel speech separation…”
Get full text

Towards Unified All-Neural Beamforming for Time and Frequency Domain Speech Separation by Gu, Rongzhi, Zhang, Shi-Xiong, Zou, Yuexian, Yu, Dong

“…Recently, frequency domain all-neural beamforming methods have achieved remarkable progress for multichannel speech separation. In parallel, the integration of…”
Get full text

Interest degree of products analysis by RFID technology for offline shops marketing optimization by Xin Su, Rongzhi Gu, Can Qi, Xuewu Zhang, Dongmin Choi

“…With the booming of e-commerce, salerooms of online shops have affected the offline shops marketing severely. It requires a smart system to help dealers to…”
Get full text

TSpeech-AI System Description to the 5th Deep Noise Suppression (DNS) Challenge by Yu, Jianwei, Chen, Hangting, Luo, Yi, Gu, Rongzhi, Li, Weihua, Weng, Chao

“…This report presents the development of Tencent AI Lab's personalized speech enhancement system for the 2023 ICASSP Signal Processing Grand Challenge - deep…”
Get full text

Luminescence property, energy transfer and thermal property of color tunable phosphor Ca9-wCe0.5Y0.5-x-y-z(PO4)7:xTb3+, yEu3+, zSm3+, wMn2 by Gu, Rongzhi, Guan, Mengyuan, Jiang, Na, Yuan, Tianyu, Ma, Guoquan, Wang, Chao, Yang, Zhiping, Li, Panlai, Wang, Zhijun

“…Series of Ca9-wCe0.5Y0.5-x-y-z(PO4)7:xTb3+, yEu3+, zSm3+, wMn2+ phosphors are synthesized by a high temperature solid state method. The spectral property and…”
Get full text

Luminescence property, energy transfer and thermal property of color tunable phosphor Ca^sub 9-w^Ce^sub 0.5^Y^sub 0.5-x-y-z^(PO^sub 4^)^sub 7^:xTb^sup 3+^, yEu^sup 3+^, zSm^sup 3+^, wMn^sup 2 by Gu, Rongzhi, Guan, Mengyuan, Jiang, Na, Yuan, Tianyu, Ma, Guoquan, Wang, Chao, Yang, Zhiping, Li, Panlai, Wang, Zhijun

“…Series of Ca9-wCe0.5Y0.5-x-y-z(PO4)7:xTb3+, yEu3+, zSm3+, wMn2+ phosphors are synthesized by a high temperature solid state method. The spectral property and…”
Get full text

Luminescence property, energy transfer and thermal property of color tunable phosphor Ca9-Ce0.5Y0.5---(PO4)7:xTb3+, yEu3+, zSm3+, wMn2 by Gu, Rongzhi, Guan, Mengyuan, Jiang, Na, Yuan, Tianyu, Ma, Guoquan, Wang, Chao, Yang, Zhiping, Li, Panlai, Wang, Zhijun

Get full text

Learning Decoupling Features Through Orthogonality Regularization by Wang, Li, Gu, Rongzhi, Zhuang, Weiji, Gao, Peng, Wang, Yujun, Zou, Yuexian

“…Keyword spotting (KWS) and speaker verification (SV) are two important tasks in speech applications. Research shows that the state-of-art KWS and SV models are…”
Get full text

Parameter-Efficient Transfer Learning of Pre-Trained Transformer Models for Speaker Verification Using Adapters by Peng, Junyi, Stafylakis, Themos, Gu, Rongzhi, Plchot, Oldrich, Mosner, Ladislav, Burget, Lukas, Cernocky, Jan

“…Recently, the pre-trained Transformer models have received a rising interest in the field of speech processing thanks to their great success in various…”
Get full text

Fast Random Approximation of Multi-Channel Room Impulse Response by Luo, Yi, Gu, Rongzhi

“…The training of modern neural-network-based speech processing systems typically requires a large amount of reverberant data to make the systems robust against…”
Get full text

ReZero: Region-customizable Sound Extraction by Gu, Rongzhi, Luo, Yi

“…We introduce region-customizable sound extraction (ReZero), a general and flexible framework for the multi-channel region-wise sound extraction (R-SE) task…”
Get full text

Fast Random Approximation of Multi-channel Room Impulse Response by Luo, Yi, Gu, Rongzhi

“…Modern neural-network-based speech processing systems are typically required to be robust against reverberation, and the training of such systems thus needs a…”
Get full text

3D Neural Beamforming for Multi-channel Speech Separation Against Location Uncertainty by Gu, Rongzhi, Zhang, Shi-Xiong, Yu, Dong

“…Multi-channel speech separation using speaker's directional information has demonstrated significant gains over blind speech separation. However, it has two…”
Get full text

Temporal-Spatial Neural Filter: Direction Informed End-to-End Multi-channel Target Speech Separation by Gu, Rongzhi, Zou, Yuexian

“…Target speech separation refers to extracting the target speaker's speech from mixed signals. Despite the recent advances in deep learning based close-talk…”
Get full text