基于谱信息熵和互补模型的声效模式检测

doi:10.13190/j.jbupt.2017-157

北京邮电大学学报 ›› 2018, Vol. 41 ›› Issue (2): 56-61.doi: 10.13190/j.jbupt.2017-157

基于谱信息熵和互补模型的声效模式检测

晁浩, 鲁保云, 刘永利, 刘志中, 宋成

河南理工大学计算机科学与技术学院, 河南焦作 454000

收稿日期:2017-08-10 出版日期:2018-04-28 发布日期:2018-03-17
作者简介:晁浩(1981-),男,讲师,E-mail:chaohao1981@163.com.
基金资助:
国家自然科学基金项目（61502150，61403128）；河南省高等学校青年骨干教师资助项目（2015GGJS-068）；河南省科技攻关项目（172102210279）

Vocal Effort Detection Based on Spectral Information Entropy and Complementary Models

CHAO Hao, LU Bao-yun, LIU Yong-li, LIU Zhi-zhong, SONG Cheng

School of Computer Science and Technology, Henan Polytechnic University, Henan Jiaozuo 454000, China

Received:2017-08-10 Online:2018-04-28 Published:2018-03-17

摘要/Abstract

摘要： 提出了一种基于模型融合的声效检测方法.首先提取对所有声效模式都具有良好辨识能力的谱信息熵特征，并进行声效辨识度分析；然后引入互补模型进行声效识别，从模型层面实现了整体谱特征、梅尔频率倒谱系数和谱信息熵的融合.对孤立词测试集进行了声效检测实验，识别精度为81.6%，实验结果表明，谱信息熵在3类特征中具有最好的分类能力，而互补模型能够有效集成3种特征蕴含的显著性信息.

关键词: 声效, 谱信息熵, 支持向量机, 高斯混合模型, 多层感知器

Abstract: A new vocal effort detection method based on model fusion was presented. By analyzing the ability to discriminate the vocal effort modes, the spectral information entropy feature which contains more salient information regarding the vocal effort level was proposed. Then, the complementary models were presented to achieve the fusion of the spectrum features, Mel-frequency cepstral coefficients and spectral information entropy feature. Experiments are conducted on isolated words test set, and the proposed method achieves 81.6% average recognition accuracy. The results show the spectral information entropy has the best performance among the three kinds of features and the complementary models can integrate the three kinds of features effectively.

Key words: vocal effort, spectral information entropy, support vector machine, Gaussian mixture model, multilayer perceptron

中图分类号:

TN391.42

晁浩, 鲁保云, 刘永利, 刘志中, 宋成. 基于谱信息熵和互补模型的声效模式检测[J]. 北京邮电大学学报, 2018, 41(2): 56-61.

CHAO Hao, LU Bao-yun, LIU Yong-li, LIU Zhi-zhong, SONG Cheng. Vocal Effort Detection Based on Spectral Information Entropy and Complementary Models[J]. JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM, 2018, 41(2): 56-61.

参考文献

[1] Hartmut T, Anders E. Acoustic effects of variation in vocal effort by men, women, and children[J]. Journal of the Acoustical Society of America, 2000, 107(6):3438-3451.
[2] Ghaffarzadegan S, Bo?il H, Hansen JHL. UT-rocal effort Ⅱ:analysis and constrained-lexicon recognition of whispered speech[C]//ICASSP. Florence:IEEE, 2014:2563-2567.
[3] Saeidi R, Alku P, Backstrom T. Feature extraction using power-law adjusted linear prediction with application to speaker recognition under severe vocal effort mismatch[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2016, 24(1):42-53.
[4] Tumomo R, Antti Suni, Jouni P, et al. Analysis and synthesis of shouted speech[C]//Interspeech. Lyon:ISCA, 2013:1544-1548.
[5] Zhang Chi, Hansen, John H L. Advancements in whisper-island detection within normally phonated audio streams[C]//Interspeech. Brighton:ISCA, 2009:860-863.
[6] Carlin M A, Smolenski B Y, Wenndt S J. Unsupervised detection of whispered speech in the presence of normal phonation[C]//Interspeech. Pittsburgh:ISCA, 2006:685-688.
[7] Zhang Chi, Hansen, John H L. Analysis and classification of speech mode:whispered through shouted[C]//Interspeech. Antwerp:ISCA, 2007:2289-2292.
[8] Petr Z, Milan S, Jiri S. Impact of vocal effort variability on automatic speech recognition[J]. Speech Communication, 2012, 54(6):732-742.
[9] 晁浩, 宋成, 刘志中. 基于元音模板匹配的声效多级检测[J]. 北京邮电大学学报, 2016, 39(4):98-102. Chao Hao, Song Cheng, Liu Zhizhong. Multi-level detection of vocal effort based on vowel template matching[J]. Journal of Beijing University of Posts and Telecommunications, 2016, 39(4):98-102.
[10] Ni Chongjia, Liu Wenju, Xu Bo. Mandarin prosodic break detection based on complementary model[C]//ISCSLP. Tainan:IEEE, 2011:353-357.
[11] Ni Chongjia, Liu Wenju, Xu Bo. From English pitch accent detection to mandarin stress detection, where is the difference?[J]. Computer Speech & Language, 2012, 26(3):127-148.
[12] Chang Chihchung and Lin Chihjen. LIBSVM:a library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology, 2011, 2(3):1-27.

[1]	田中大潘信澎. 小波消噪和优化支持向量机的网络流量预测[J]. 北京邮电大学学报, 2022, 45(5): 79-84.
[2]	赵雄文, 孙宁姚, 耿绥燕, 张钰, 杜飞. 基于最小二乘支持向量机的时变信道建模[J]. 北京邮电大学学报, 2019, 42(5): 29-35.
[3]	孙朝宇, 高守婉, 杨旭, 陈朋朋, 牛强. 基于信道状态信息的矿难人员检测研究[J]. 北京邮电大学学报, 2019, 42(4): 96-101.
[4]	韦娟, 张芃楠, 岳凤丽, 宁方立. 基于PSO-PF算法的SVM识别方法及其在异常声音中的应用[J]. 北京邮电大学学报, 2019, 42(3): 58-63.
[5]	吴青, 齐韶维, 孙凯悦, 臧博研, 赵祥. 最小二乘大间隔孪生支持向量机[J]. 北京邮电大学学报, 2018, 41(6): 34-38.
[6]	马宇鹏, 张建国, 邱继伟. 基于Bootstrap-SVR-SOC的小子样结构机构可靠性分析方法[J]. 北京邮电大学学报, 2018, 41(4): 81-85.
[7]	刘春红, 韩晶晶, 商彦磊. 基于SVM分类的云集群失败作业主动预测方法[J]. 北京邮电大学学报, 2016, 39(5): 104-109.
[8]	晁浩, 宋成, 刘志中. 基于元音模板匹配的声效多级检测[J]. 北京邮电大学学报, 2016, 39(4): 98-102.
[9]	赵建龙, 曲桦, 赵季红, 戴慧珺. 基于Morlet-SVR和ARIMA组合模型的网络流量预测[J]. 北京邮电大学学报, 2016, 39(2): 53-57.
[10]	姜晓庆, 夏克文, 夏莘媛, 祖宝开. 采用半定规划多核SVM的语音情感识别[J]. 北京邮电大学学报, 2015, 38(s1): 67-71.
[11]	孟洛明, 朱杰辉, 杨杨, 孟玲莉, 张平平, 高志鹏. 支持向量机回归预测在网络故障检测中的应用[J]. 北京邮电大学学报, 2014, 37(s1): 23-29.
[12]	董航, 李祺, 董枫, 彭勇, 徐国爱. Android运行时恶意行为检测模型研究[J]. 北京邮电大学学报, 2014, 37(3): 58-61,88.
[13]	张素香. 智能小区的商业智能[J]. 北京邮电大学学报, 2012, 35(5): 94-97.
[14]	伍春李颖易克初. GA-LSSVM的认知无线电离线学习[J]. 北京邮电大学学报, 2012, 35(2): 90-93.
[15]	董秀则张茹钮心忻. MB隐写分析算法[J]. 北京邮电大学学报, 2012, 35(2): 99-103.

基于谱信息熵和互补模型的声效模式检测

Vocal Effort Detection Based on Spectral Information Entropy and Complementary Models

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价