Effect of Reverberation Phenomena on Text- independent Speaker Recognition Based Deep Learning

Speaker recognition is one of many biometric authentications, due to its high importance in many applications of security considerations and telecommunications. The main aspiration of speaker recognition system is to know who is speaking depending on voice characteristics. Many current researches focuses on text-dependent speaker recognition which has a pre-knowledge of what utterance the speaker will say. In this paper text-independent speaker recognition system is used, where no prior knowledge is accessible in the context of the speakers’ utterances for all stages. A Convolutional Neural Network (CNN) based feature extraction is extended to a text-independent Speaker recognition task. Also the effect of reverberation on speaker recognition is addressed. All the speech signals are converted into images by obtaining their spectrograms. A proposed CNN model is presented to enhance the performance of the system in case of a reverberant signal. It depends on image processing concepts, and hence spectrograms of signals are used. The proposed model is compared with a conventional benchmark model. The performance of the recognition system is measured by the recognition rate in the case of clean and reverberant data.