Sound event detection in real life recordings using coupled matrix factorization of spectral representations and class activity annotations
2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)(2015)
摘要
Methods for detection of overlapping sound events in audio involve matrix factorization approaches, often assigning separated components to event classes. We present a method that bypasses the supervised construction of class models. The method learns the components as a non-negative dictionary in a coupled matrix factorization problem, where the spectral representation and the class activity annotation of the audio signal share the activation matrix. In testing, the dictionaries are used to estimate directly the class activations. For dealing with large amount of training data, two methods are proposed for reducing the size of the dictionary. The methods were tested on a database of real life recordings, and outperformed previous approaches by over 10%.
更多查看译文
关键词
coupled non-negative matrix factorization,non-negative dictionaries,sound event detection
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络