吕勇

姓  名:吕勇性  别:出生年月:1979年2月
职  称:副教授毕业学校:东南大学
专 业:信息与通信工程学 位:  博士
联系电话:
电子邮件:yonglu@hhu.edu.cn
研究方向:

多媒体信号处理,音频信号处理

获奖情况:
主要成果:


 主要论著:

[1]Yong Lü, Zhenyang Wu, Maximum likelihood subband polynomial regression for robust speech recognition, Applied Acoustics, 74 (5), 640–646, 2013.

[2]Yong Lü, Haiyang Wu, Lin Zhou, Zhenyang Wu, Multi-environment model adaptation based on vector Taylor series for robust speech recognition, Pattern Recognition, 43(9), 3093-3099, 2010.

[3]Yong Lü, Haiyang Wu and Zhenyang Wu, Robust speech recognition using improved vector Taylor series algorithm for embedded systems, IEEE Transactions on Consumer Electronics, 56(2), 764-769, 2010.

[4]吕勇, 吴镇扬, 基于矢量泰勒级数的模型自适应算法, 电子与信息学报, 32(1), 107-111, 2010.

[5]吕勇, 吴镇扬, 基于最大似然多项式回归的鲁棒语音识别, 声学学报, 35(1), 88-96, 2010.

[6]吕勇, 吴镇扬, 基于矢量泰勒级数的鲁棒语音识别, 天津大学学报, 44(3), 261-265, 2011.

[7]吕勇, 吴镇扬, 基于最大似然子带线性回归的鲁棒语音识别, 信号处理, 26(1), 74-79, 2010.

[8]Yong Lü, Lin Zhou, Model adaptation based on improved variance estimation for robust speech recognition, 2012 International Conference on Wireless Communications and Signal Processing  WCSP 2012.

[9]Yong Lü, Lin Zhou, Model Adaptation Algorithm Based on Central Subband Regression for Robust Speech Recognition, 2014 7th International Symposium on Computational Intelligence and Design, 2014.

[10]Yong Lü, Lin Zhou, Log-Spectral Linear Regression Based on Voicing Cut-Off Frequency for Robust Speech Recognition, 2015 8h International Symposium on Computational Intelligence and Design, 2015.

发明专利:

[1]一种用于语音识别系统的多环境特征补偿方法 ZL201210488431.8.

[2]语音识别系统中基于快速噪声估计的特征补偿方法 ZL201210486936.0.

[3]一种基于声学模型阵列的鲁棒语音识别方法ZL201410699802.6.

[4]一种用于语音识别系统的中心子带模型自适应方法ZL201410695733.1


在研项目:

[1]基于音节模型的音频点播关键技术研究,国家自然科学基金,61301218,主持

[2]鲁棒语音识别中的数据稀疏问题研究,中央高校基本科研业务费,2011B09214,主持

[3]面向多媒体内容版权保护的视频水印理论研究,国家自然科学基金,61170297,参与