©2016, IJCERT All Rights Reserved DOI:10.22362/ijcert/2016/v3/i11/XXXX Page | 580 Volume 3, Issue 11, November-2016, pp. 580-584 ISSN (O): 2349-7084 International Journal of Computer Engineering In Research Trends A Survey on: Sound Source Separation Methods 1 Ms. Monali R. Pimpale, 2 Prof. Shanthi Therese , 3 Prof. Vinayak Shinde, 1 Department of Computer Engineering, Mumbai University, Shree L.R. Tiwari College of Engineering and Technology,Mira Road, India. 2 Department of Information Technology, Mumbai University, Thadomal College of Engineering and Technology,Mumbai, India 3 Department of Information Technology, Mumbai University, Shree L.R. Tiwari College of Engineering and Technology,Mira Road, India Abstract — now a day’s multimedia databases are growing rapidly on large scale. For the effective management and exploration of large amount of music data the technology of singer identification is developed. With the help of this technology songs performed by particular singer can be clustered automatically. To improve the Performance of singer identification the technologies are emerged that can separate the singing voice from music accompaniment. One of the methods used for separating the singing voice from music accompaniment is non-negative matrix partial co factorization. This paper studies the different techniques for separation of singing voice from music accompaniment. Keywords—singer identification, non-negative matrix partial co factorization ——————————  —————————— I.INTRODUCTION The development of singer identification enables the effective management of large amounts of music data. With this singer identification technology, songs performed by a particular singer can be automatically clustered for easy management or searching. There are many algorithms which are used for singer identification which are based on the concept of feature extraction which identifies the appropriate singer from the obtained features. In popular music, singing voice is combined with music accompaniment. So those methods based on the features extracted directly from the accompanied vocal segments are difficult to acquire good performance when accompaniment is stronger or singing voice is weaker. To get better performance the techniques are emerged which separates the singing voice from music accompaniment. There are many sound source separation algorithms which separates the singing voice from music accompaniment. Sound source separation means the tasks of evaluating the signal produced by an individual sound source from a mixture signal consisting of multiple sources. This is a very fundamental problem in many audio signal processing tasks, since analysis and processing of isolated or single sources can be done with much better accuracy than the processing of mixtures of sounds. The term unsupervised learning is used to characterize algorithms which try to separate and learn the structure of sound sources in mixed data based on information-theoretical principles, such as statistical independence between sources, instead of highly sophisticated modeling of the source characteristics or human auditory perception. There are many unsupervised learning sound source separation algorithm some of them are independent component analysis (ICA), sparse coding, and non- Available online at: www.ijcert.org