Institute of Electrical & Electronic Engineers
In this paper, the authors present a novel system for joint speaker identification and speech separation. For speaker identification a single-channel speaker identification algorithm is proposed which provides an estimate of Signal-to-Signal Ratio (SSR) as a by-product. For speech separation, they propose a sinusoidal model-based algorithm. The speech separation algorithm consists of a double-talk/single-talk detector followed by a minimum mean square error estimator of sinusoidal parameters for finding optimal code-vectors from pre-trained speaker codebooks. In evaluating the proposed system, they start from a situation where they have prior information of codebook indices, speaker identities and SSR-level, and then, by relaxing these assumptions one by one, they demonstrate the efficiency of the proposed fully blind system.