Statistical Speech Model Description with VMF Mixture Model
This is an incremental improvement in speech coding for compression applications.
The paper tackles the problem of modeling LSF parameters in speech coding by representing them as unit vectors and using a von Mises-Fisher mixture model, resulting in a VMM-based vector quantization method that outperforms DVQ and GVQ in experiments.
In this paper, we present the LSF parameters by a unit vector form, which has directional characteristics. The underlying distribution of this unit vector variable is modeled by a von Mises-Fisher mixture model (VMM). With the high rate theory, the optimal inter-component bit allocation strategy is proposed and the distortion-rate (D-R) relation is derived for the VMM based-VQ (VVQ). Experimental results show that the VVQ outperforms our recently introduced DVQ and the conventional GVQ.