Real Facial expression acknowledgment (RTFER) has become a functioning examination zone that finds a ton of utilizations in territories like human-PC interfaces, human feeling investigation, mental investigation, clinical conclusion and so on Mainstream strategies utilized for this intention depend on math and appearance. Profound convolutional neural networks (CNN) have appeared to beat customary strategies in different visual acknowledgment errands including Facial Expression Recognition. Despite the fact that endeavours are made to improve the exactness of RTFER frameworks utilizing CNN, for functional applications existing strategies probably won't be adequate. This examination incorporates a conventional audit of RTFER frameworks utilizing CNN and their qualities and restrictions which assist us with comprehension and improve the RTFER frameworks further.

In this paper watermark is embedded into audio signal by modifying the samples data with the watermark key. An unvoiced and voiced data with payload equal to 16000 Hz is used for the simulation. Under different noise adding conditions the performance of the system is evaluated. Also in this paper performance of the algorithm is analyzed by varying the bit modification location of the 8 bit sample from LSB to MSB. MATLAB is used for the simulation purpose.