Improved use of deep belief networks for voice activity detection

Abstract

Abstract: Focusing on existing methods are too complicated and in order to make better use of the deep belief networks for voice activity detection, an improved voice spectrum as deep belief networks’input is used in this paper. Simulation experiments use TIMIT corpus with the Matlab, experimental results verify the validity of the method, and show that this method has higher detection accuracy percentage of the examination than existing methods in Babble environments.

Key words: voice activity detection, deep belief networks, fast Fourier transform, speech signal processing

摘要： 为了更好地运用深度置信网络进行语音端点检测，针对现有方法过于繁杂的问题，改进采用语音频谱作为深度置信网络的输入。在Matlab环境下使用TIMIT语料库进行仿真实验，实验结果验证了该方法的有效性，并且在Babble噪声环境下验证该方法比现有方法具有更高的检测正确率。

关键词: 语音端点检测, 深度置信网络, 快速傅里叶变换, 语音信号处理

TIAN Wanglan, LI Jiasheng. Improved use of deep belief networks for voice activity detection[J]. Computer Engineering and Applications, 2014, 50(20): 207-210.

田旺兰，李加升. 改进运用深度置信网络的语音端点检测方法[J]. 计算机工程与应用, 2014, 50(20): 207-210.

[1]	XU Xianfeng, CAI Lulu, ZHANG Li. Photovoltaic Power Generation Prediction Algorithm Based on MLP and DBN [J]. Computer Engineering and Applications, 2021, 57(3): 266-272.
[2]	WANG Shiqi, ZENG Qingning, LONG Chao, XIONG Songling, QI Xiaoxiao. Multi-task Learning for Speech Enhancement and Detection [J]. Computer Engineering and Applications, 2021, 57(20): 197-202.
[3]	KANG Mengxuan, SONG Junping, FAN Pengfei, GAO Bowen, ZHOU Xu, LI Zhuo. Survey of Network Traffic Forecast Based on Deep Learning [J]. Computer Engineering and Applications, 2021, 57(10): 1-9.
[4]	CHEN Qiuju, XU Jianguo. Optimized Orthogonal Matching Pursuit and Short-Time Spectrum Estimation for Sound Recognition [J]. Computer Engineering and Applications, 2020, 56(7): 162-169.
[5]	CHEN Hong, WANG Runting, XIAO Chenglong, GUO Pengfei, HUANG Jie, CHEN Honglin. Research on Intrusion Detection Model Based on DBN-XGBDT [J]. Computer Engineering and Applications, 2020, 56(22): 83-91.
[6]	LIU Ruilan, MAO Jiamin. Soft sensor modeling of 4-CBA based on deep belief networks [J]. Computer Engineering and Applications, 2017, 53(6): 227-230.
[7]	LIU Jinyi1, ZHANG Le1，2, HU Haibo1，2, ZU He3. Strong robustness human activity recognition based on wearable sensors [J]. Computer Engineering and Applications, 2017, 53(4): 176-183.
[8]	PENG Ziran1, WANG Guojun1，2. Study on parallel algorithm of wavelet transform based on MPSoC platform [J]. Computer Engineering and Applications, 2017, 53(4): 33-38.
[9]	LAI Songxuan, LI Yanxiong. Generating initial clusters for speaker clustering [J]. Computer Engineering and Applications, 2017, 53(3): 149-153.
[10]	SONG Lijuan. Recognition model of disease image based on discriminative deep belief networks [J]. Computer Engineering and Applications, 2017, 53(21): 32-36.
[11]	EN De1, CHEN Yake1, MAO Zhelong2. Discontinuous transmission of voice in L-PLC under low SNR based on FastICA [J]. Computer Engineering and Applications, 2016, 52(9): 108-111.
[12]	ZHAO Qipeng1, SUN Yongxuan1, HONG Yan2, YAO Tingting1, XIE Zhao1. Real-time multi-object tracking with structure priors [J]. Computer Engineering and Applications, 2016, 52(4): 174-180.
[13]	LI Ling, LUO Zhengping, YANG Tianqi. Gait recognition method based on space mass energy image and Dynamic Space Warping [J]. Computer Engineering and Applications, 2016, 52(3): 127-132.
[14]	WANG Min, HUANG Fei, LIU Li, WEI Mingfei, WANG Mingming. Voice conversion using deep belief networks [J]. Computer Engineering and Applications, 2016, 52(15): 168-171.
[15]	ZHANG Lie1, FENG Yan1, LI Lin2. Optimized calculation for digital pre-distortion based on frequency selective compressive sampling [J]. Computer Engineering and Applications, 2015, 51(20): 102-106.

Improved use of deep belief networks for voice activity detection

改进运用深度置信网络的语音端点检测方法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics