期刊名称：Journal of Emerging Trends in Computing and Information Sciences
电子版ISSN：2079-8407
出版年度：2011
卷号：2
期号：10
页码：525-528
出版社：ARPN Publishers
摘要：Speech processing is used widely in every application that most people take for granted, such as network wire lines, cellular telephony, telephony system and telephone answering machines. Due to its popularity and increasing of demand, engineers are trying various approaches of improving the process. One of the methods for improving the process is MMSE based Wiener filter. The objective of speech enhancement is to improve the quality of a speech signal, often degraded by some type of distortion (for example communication channel distortion, additive noise, convolution filtering operation, etc.)The quality of a speech signal is judged, depending on the application, by one or more of the following factors intelligibility, perceptual quality, listener fatigue, signal-to-noise ratio (SNR), speech distortion, and (occasionally) recognition accuracy of an automatic speech recognizer. Numerous schemes have been proposed and implemented that perform speech enhancement under various constraints/assumptions and deal with different issues and applications An application of these estimators in an auditory enhancement scheme using the masking threshold of the human auditory system is formulated, resulting in the GMMSE auditory masking threshold (AMT) enhancement method. Finally, a detailed evaluation Proposed algorithms are performed over the audio archive using subjective and objective speech quality measures.
