Robust Formant Tracking Algorithm in Real Time Noise Environment

资源类型: 资源大小: 文档分类: 上传者:李德翠

文档信息

【标题】Robust Formant Tracking Algorithm in Real Time Noise Environment

【作者】 Mandeep Singh Walia 

【摘要】The traditional approaches for formant frequency estimation are misled by spectral peaks in unvoiced speech and perform very poorly in transient background noise. Also; these traditional algorithms are not robust in real life noise environment and are unable to recover quickly after periods of silence. Robust formant tracking algorithm is discussed. Testing of the algorithm using various speech sentences has shown promising results over a wide range of signal to noise ratio’s (SNR’s) for various types of background included the babble (crowd of people); car; exhibition hall; restaurant; street; airport; train station and train recordings from different places. By observing the limitations of the traditional formant tracking algorithms it can be seen that the robust formant tracking algorithm is the most accurate algorithm. Results from algorithm showed that the robust formant tracking algorithm gives very good tracking performance in every environment.

问答

我要提问