Speech denoising and syllable segmentation based on fractal dimension

Computer Engineering and Applications ›› 2011, Vol. 47 ›› Issue (14): 131-133.

• 数据库、信号与信息处理 • Previous Articles Next Articles

Speech denoising and syllable segmentation based on fractal dimension

PAN Feng1，2，DING Nana1，LV Peng3，SHEN Junwei4

1.Key Lab of Network & Information Security，Chinese Armed Police Force，Engineering Institute of the Armed Police，Xi’an 710086，China
2.Key Laboratory of Network & Information Security of the Ministry of Education，Xidian University，Xi’an 710071，China
3.College of Information Engineering，Shijiazhuang University of Science and Technology，Shijiazhuang 050021，China
4.Electronic Department，Engineering Institute of the Armed Police，Xi’an 710086，China

Received:1900-01-01 Revised:1900-01-01 Online:2011-05-11 Published:2011-05-11

基于分形维的语音去噪与音节分割

潘峰1，2，丁娜娜1，吕鹏3，申军伟4

1.武警工程学院电子技术系网络与信息安全武警部队重点实验室，西安 710086
2.西安电子科技大学网络信息安全教育部重点实验室，西安 710071
3.石家庄科技大学信息工程学院，石家庄 050021
4.武警工程学院电子技术系机要指挥教研室，西安 710086

Abstract

Abstract: In order to enhance the effect of existing wavelet denoising and determine beginning-ending points of each syllable in continuous speech，the thesis proposes an algorithm based on fractal theory.The algorithm first uses dynamic threshold algorithm which combines fractal dimension with wavelet transform to denoise the speech signal，it can extract pure speech as far as possible;on this basis，the paper designs the algorithm which is based on the mean of fractal dimension trajectory to carry out syllable segmentation.The experimental results show that the algorithms not only achieves speech denoising and syllable segmentation but also has good robustness.In the case of low SNR，the algorithm is still able to maintain high accuracy rate.It has better prospect in speech recognition field.

Key words: speech recognition, fractal dimension, speech denoising, syllable segmentation

摘要： 为提高现有小波去噪法的处理效果，准确有效判断出连续语音中各个音节的起止点，提出了基于分形理论的算法。该算法首先利用分形维与小波变换相结合的动态阈值算法进行语音去噪，从而提取出尽可能纯净的语音信号;在此基础上，计算分形维轨线，根据其均值对音节分割点进行判定。实验结果表明，该算法较好地实现了语音去噪和音节分割，鲁棒性较好，使得系统在低信噪比情况下仍保持较高准确率，在语音识别方面有较好应用前景。

关键词: 语音识别, 分形维, 语音去噪, 音节分割

PAN Feng1，2，DING Nana1，LV Peng3，SHEN Junwei4. Speech denoising and syllable segmentation based on fractal dimension[J]. Computer Engineering and Applications, 2011, 47(14): 131-133.

潘峰1，2，丁娜娜1，吕鹏3，申军伟4. 基于分形维的语音去噪与音节分割[J]. 计算机工程与应用, 2011, 47(14): 131-133.

[1]	FENG Xuemei, ZHANG Zhiyi, YANG Long. Global Point Cloud Initial Registration Algorithm of Fractal Dimension [J]. Computer Engineering and Applications, 2020, 56(5): 234-241.
[2]	LOU Yingdan, XU Jinglin, HUANG Lixia, ZHANG Xueying. Speech Recognition Based on MLLR and MAP Under Distant Noise Reverberation Environment [J]. Computer Engineering and Applications, 2020, 56(10): 122-126.
[3]	ZHAO Yue, LI Yaoqiang, XU Xiaona, WU Licheng. Near-optimal active learning for Tibetan speech recognition [J]. Computer Engineering and Applications, 2018, 54(22): 156-159.
[4]	HUANG Xiaohui1，2, LI Jing1, MA Rui2，3. Design and research of Tibetan spoken speech corpus [J]. Computer Engineering and Applications, 2018, 54(13): 231-235.
[5]	SONG Chunxiao, SUN Ying. Nonlinear geometric feature extraction algorithm for emotional speech recognition [J]. Computer Engineering and Applications, 2017, 53(20): 128-133.
[6]	HUANG Lixia1, WANG Yanan1, ZHANG Xueying1, WANG Hongcui2. Research on noise robustness of speech recognition based on deep auto-encoder neural network [J]. Computer Engineering and Applications, 2017, 53(13): 49-54.
[7]	CHEN Xiaojuan1, WANG Danhui2. Face recognition based on BEMD and fractal dimension [J]. Computer Engineering and Applications, 2017, 53(10): 177-180.
[8]	ZHAO Caiguang, ZHANG Shuqun, LEI Zhaoyi. Improved speech recognition of GRBM based on parallel tempering [J]. Computer Engineering and Applications, 2016, 52(8): 125-129.
[9]	Dawel Abilhayer, Nurmemet Yolwas, LIU Yan. On language model construction for LVCSR in Kazakh [J]. Computer Engineering and Applications, 2016, 52(24): 178-181.
[10]	QIN Jianqiang1, KONG Xiangyu1, HU Shaolin2, MA Hongguang3. Performance comparison of methods for estimating fractal dimension of time series [J]. Computer Engineering and Applications, 2016, 52(22): 33-38.
[11]	CHAO Hao, SONG Cheng, XUE Xiao, LIU Zhizhong. Vocal effort related robust speech recognition based on adaptation method [J]. Computer Engineering and Applications, 2016, 52(2): 156-160.
[12]	CHAO Hao. Decoding algorithm of integrating phonetic string edit distance into stochastic segment models [J]. Computer Engineering and Applications, 2015, 51(6): 208-211.
[13]	WU Xiaoxuan, NI Zhiwei, NI Liping. Research on fractal clustering ensemble algorithm based on cloud computing environment [J]. Computer Engineering and Applications, 2015, 51(14): 1-6.
[14]	WU Man, ZHANG Gongrang, LIU Heng. Feature selection based on fractal dimension and multi-objective genetic algorithm [J]. Computer Engineering and Applications, 2015, 51(11): 109-113.
[15]	Alim MURAT, Azragul, Yusup ABAYDUL. Research on key issue of modern Uyghur language personal name to Chinese transliteration [J]. Computer Engineering and Applications, 2014, 50(9): 209-213.

Speech denoising and syllable segmentation based on fractal dimension

基于分形维的语音去噪与音节分割

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics