Over the past decades, a tremendous amount of research has been done on the use of machine learning for speech processing applications, especially speech recognition. However, in the past few years, research has focused on utilizing deep learning for speech-related applications. This new area of machine learning has yielded far better results when compared to others in a variety of applications including speech, and thus became a very attractive area of research. This paper provides a thorough examination of the different studies that have been conducted since 2006, when deep learning first arose as a new area of machine learning, for speech applications. A thorough statistical analysis is provided in this review which was conducted by extracting specific information from 174 papers published between the years 2006 and 2018. The results provided in this paper shed light on the trends of research in this area as well as bring focus to new research topics. INDEX TERMS Speech recognition, deep neural network, systematic review.

No abstract

This paper reviews single stage amplifiers identified in the literature as well as presents a new structure single stage highly linear rail-to-rail amplifier intended for column drivers in Active Matrix Liquid Crystal Display (AMLCD). The new proposed amplifier is based on applying current splitting technique on a rail-to-rail differential pair thus elevating the overall performance of the amplifier in terms of different performance parameters such as effective transconductance, output resistance, DC gain and unity gain frequency among others. One major advantage of the new proposed amplifier is its capability of providing a rail-to-rail stable operation without the need for compensation. The performance of the new proposed amplifier is tested on LTspice using 90nm CMOS technology under 1 Volts supply voltage and compared to other existing single stage amplifiers. Simulation results shows that the proposed amplifier provides a high DC gain, high effective transconductance and high output resistance while maintaining a stable operation with a phase margin of 80 •. Obtained results also confirms that the amplifier exhibits rail-to-rail operation while maintaining a very low Total Harmonic Distortion (THD). The pulse response of the proposed amplifier indicates a fast response with a rise time and fall times almost twice as fast as the other examined topologies. Against Process, Voltage and Temperature (PVT) variations, the amplifier exhibits a robust performance as the DC gain variation range was within 20% only which is much less than the other examined topologies.

No abstract

No abstract