Speaker Attractor Network: Generalizing Speech Separation to Unseen Numbers of Sources
Fei Jiang, Zhiyao Duan · IEEE Signal Processing Letters · 2020
Most existing speech separation research focuses on improving the separation performance under consistent source number conditions between training and testing. In real-world applications, however, the source number may be different from that in training sets. In this letter, we address this problem by thoroughly improving the deep attractor network in terms of the network architecture and learning objectives so that it can well generalize to separating an unseen number of sources. Experimental results show that, compared with existing models, the proposed method significantly improves the separation performance when generalizing to an unseen number of speakers, and can separate up to five speakers even the model is only trained on two-speaker mixtures.