•Signals which overlaps in both time and frequency domain, are very difficult to separate out without distortion.•In multimedia content making, sound plays a vital role.•Deep Neural Networks (DNN)have been used to handle the full separation of overlapping sources.•DNNs for audio signal separation depends on factors such as the quality, size of the training data, architecture of the network, and the specific task at hand. Separating the signals from the mixture when the signals share same frequency and time domain pattern is always a matter of concern. In natural environment, sound events often appear simultaneously, increasing the complexity. Movie making and audio-visual content creation is an industry which covers a huge share of our economy. With the advancement of technology, it becomes important to give audience more realistic experience. But sometimes due to certain environmental conditions, recording devices capture sound signals which overlap with the character voice of the script or required ambience sound either in frequency domain or time domain or in both. To fix the problem, sound engineers mostly dub the sound in the studio and try to collect the ambience sound later on. Further mixing is done during post processing of sound. Although different software tools are available in market, but here aesthetic value and originality of the sound has been compromised. Because, it is very hard to get the exact voice parameters and same ambience in studio environment. This paper gives an overview of different approaches to deal with the overlapping sound by focussing the recently reported literature and highlights the key attributes which are catalysing the evolving scenario.