期刊文献+

基于语音交互的阅读绘本器发音准确性检测模型构建

Construction of pronunciation accuracy detection model of reading picture book based on voice interaction
原文传递
导出
摘要 阅读绘本器发音准确性是提升阅读绘本质量的关键,提出基于语音交互的阅读绘本器发音准确性检测模型构建方法。采用语音传感器实现对阅读绘本器的语音信息检测,建立阅读绘本器发音语音信号模型,采用数字化滤波检测方法进行阅读绘本器发音语音特征检测和谱分析,采用语音交互和语音增强方法,建立阅读绘本器发音语音特征检测和噪声分离模型,在给定虚警概率下建立最优阅读绘本器发音语音信号检测模型,在先验多普勒频率范围内提高阅读绘本器发音准确性检测能力。仿真结果表明,采用该方法进行阅读绘本器发音检测的准确概率较高,虚警概率较小,提高了阅读绘本器的语音交互和动态特征分析能力。 The pronunciation accuracy of reading picture books is the key to improve the quality of reading picture books.This paper puts forward a method to build the pronunciation accuracy detection model of reading picture books based on voice interaction.The voice sensor is used to detect the voice information of the picture book reader,the picture book reader pronunciation voice signal model is established,the picture book reader pronunciation voice feature detection and spectrum analysis are carried out by digital filtering detection method,the picture book reader pronunciation voice feature detection and noise separation model is established by voice interaction and voice enhancement method,the optimal picture book reader pronunciation voice signal detection model is established under a given false alarm probability,and the pronunciation accuracy detection ability of the picture book reader is improved within the range of prior Doppler frequency.The simulation results show that this method has higher accurate probability and lower false alarm probability in pronunciation detection of picture book reader,which improves the ability of speech interaction and dynamic feature analysis of picture book reader.
作者 张雷 ZHANG Lei(Shaanxi Xueqian Normal University,Xi’an 710100,China)
出处 《自动化与仪器仪表》 2022年第7期45-48,共4页 Automation & Instrumentation
基金 陕西学前师范学院科研基金项目《以陕西省非物质文化遗产名录中民间文学为素材的儿童绘本创作研究》(2020YBRS40)。
关键词 语音交互 阅读绘本器 发音准确性 检测模型 voice interaction reading picture book device accuracy of pronunciation detection model
  • 相关文献

参考文献13

二级参考文献71

  • 1赵兴浩,邓兵,陶然.分数阶傅里叶变换数值计算中的量纲归一化[J].北京理工大学学报,2005,25(4):360-364. 被引量:125
  • 2Ephraim Y and Malah D. Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator[J]. IEEE Transactions on Acoustic, Speech and Signal Processing, 1984, 32(6): 1109-1121.
  • 3Gazor S and Zhang W. Speech probability distribution[J]. IEEE Signal Processing Letters, 2003, 10(7): 204-207.
  • 4Martin R. Speech enhancement based oil minimum mean square error estimation and supergaussian priorsIJ]. IEEE Transactions on Speech and Audio Processing, 2005, 13(5): 845-856.
  • 5Lotter T and Vary P. Speech enhancement by MAP spectral amplitude estimation using a super-gaussian speech model[J]. EURASIP Journal on Applied Signal Processing, 2005, 2005(7): 1110-1126.
  • 6Hendriks C R, Heusdens R, and Jensen J. Log-spectral magnitude MMSE estimators under super-gaussian densities[C]. INTERSPEECH, Brighton, UK, 2009: 1319-1322.
  • 7Paliwal K, Schwerin B, and Wojcicki K. Single channel speech enhancement using MMSE estimation of short-time modulation magnitude spectrum[C]. INTERSPEECH, Florence, Italy, 2011: 1209-1212.
  • 8Esch T and Vary P. Model-based speech enhancement using SNR dependent MMSE estimation[C]. IEEE InternationalConference on Acoustics, Speech and Signal Processing, Prague, Czech, 2011: 4652-4655.
  • 9Erkelens S J, Hendriks C R, Heusdens R, et al.. Minimum mean-square error estimation of discrete fourier coeffcients with generalized Gamma priors[J]. IEEE Transactions on Audio, Speech and Language Processing, 2007, 6(15): 1741-1752.
  • 10Borgstrom J B and Alwan A. Log-spectral amplitude estimation with generalized Gamma distributions for speech enhancement[C). IEEE International Acoustics, Speech and Signal Processing 2011: 4756-4759. Conference on Prague, Czech,.

共引文献95

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部