Referenceless Performance Evaluation of Audio Source Separation Using Deep Neural Networks
arXiv:1811.00454 [cs, eess], vol.
Computer Science - Machine Learning,Computer Science - Sound,Electrical Engineering and Systems Science - Audio and Speech Processing,68T01; 68T10; 68T45; 62H25,Computer Science - Multimedia,H.5.5,I.2,I.2.6,I.4,I.4.3,I.5
- Emad M. Grais
- Hagen Wierstorf
- Dominic Ward
- Russell Mason
- Mark D. Plumbley
Current performance evaluation for audio source separation depends on comparing the processed or separated signals with reference signals. Therefore, common performance evaluation toolkits are not applicable to real-world situations where the ground truth audio is unavailable. In this paper, we propose a performance evaluation technique that does not require reference signals in order to assess separation quality. The proposed technique uses a deep neural network (DNN) to map the processed audio into its quality score. Our experiment results show that the DNN is capable of predicting the sources-to-artifacts ratio from the blind source separation evaluation toolkit without the need for reference signals.