Close-microphone techniques are extensively employed in many live music recordings, allowing for interference\r\nrejection and reducing the amount of reverberation in the resulting instrument tracks. However, despite the use of\r\ndirectional microphones, the recorded tracks are not completely free from source interference, a problem which is\r\ncommonly known as microphone leakage. While source separation methods are potentially a solution to this\r\nproblem, few approaches take into account the huge amount of prior information available in this scenario. In fact,\r\nbesides the special properties of close-microphone tracks, the knowledge on the number and type of instruments\r\nmaking up the mixture can also be successfully exploited for improved separation performance. In this paper, a\r\nnonnegative matrix factorization (NMF) method making use of all the above information is proposed. To this end, a\r\nset of instrument models are learnt from a training database and incorporated into a multichannel extension of the\r\nNMF algorithm. Several options to initialize the algorithm are suggested, exploring their performance in multiple\r\nmusic tracks and comparing the results to other state-of-the-art approaches.
Loading....