Zobrazeno 1 - 10
of 901
pro vyhledávání: '"Zhang, Xiao-lei"'
Sound Source Localization (SSL) involves estimating the Direction of Arrival (DOA) of sound sources. Since the DOA estimation output space is continuous, regression might be more suitable for DOA, offering higher precision. However, in practice, clas
Externí odkaz:
http://arxiv.org/abs/2311.12305
Recently, automatic speaker verification (ASV) based on deep learning is easily contaminated by adversarial attacks, which is a new type of attack that injects imperceptible perturbations to audio signals so as to make ASV produce wrong decisions. Th
Externí odkaz:
http://arxiv.org/abs/2310.14270
The performance of speaker verification degrades significantly in adverse acoustic environments with strong reverberation and noise. To address this issue, this paper proposes a spatial-temporal graph convolutional network (GCN) method for the multi-
Externí odkaz:
http://arxiv.org/abs/2307.01386
Recently, an end-to-end two-dimensional sound source localization algorithm with ad-hoc microphone arrays formulates the sound source localization problem as a classification problem. The algorithm divides the target indoor space into a set of local
Externí odkaz:
http://arxiv.org/abs/2304.07512
Quantum federated learning (QFL) is a quantum extension of the classical federated learning model across multiple local quantum devices. An efficient optimization algorithm is always expected to minimize the communication overhead among different qua
Externí odkaz:
http://arxiv.org/abs/2303.08116
The success of adversarial attacks to speaker recognition is mainly in white-box scenarios. When applying the adversarial voices that are generated by attacking white-box surrogate models to black-box victim models, i.e. \textit{transfer-based} black
Externí odkaz:
http://arxiv.org/abs/2302.10686
Autor:
LIU Ze-wei, YUE Ai-zhong, LI Bing, ZHAO Jing-yi, JIANG Li-ming, LIU Jiong, MA Hui-sheng, ZHANG Xiao-lei, LU Ning, WANG Shu-sheng
Publikováno v:
He huaxue yu fangshe huaxue, Vol 46, Iss 2, Pp 131-136 (2024)
The neutron tube is the core component of the controllable neutron source logging instrument. Its working stability, temperature resistance, neutron yield and other indicators have an important impact on the working performance of instrument. At pres
Externí odkaz:
https://doaj.org/article/cb797baba38546e497e3999d4042cbb8
Autor:
Liang, Chengdong, Zhang, Xiao-Lei, Zhang, BinBin, Wu, Di, Li, Shengqiang, Song, Xingchen, Peng, Zhendong, Pan, Fuping
Recently, the unified streaming and non-streaming two-pass (U2/U2++) end-to-end model for speech recognition has shown great performance in terms of streaming capability, accuracy and latency. In this paper, we present fast-U2++, an enhanced version
Externí odkaz:
http://arxiv.org/abs/2211.00941
Although the security of automatic speaker verification (ASV) is seriously threatened by recently emerged adversarial attacks, there have been some countermeasures to alleviate the threat. However, many defense approaches not only require the prior k
Externí odkaz:
http://arxiv.org/abs/2211.00825