The use of subvector quantization and discrete densities for fast GMM computation for speaker verification

TL;DRAbstract

Last year, we showed that the computation of a GMM-UBMbased speaker verification (SV) system may be sped up by 30 times by using a high-density discrete model (HDDM) on the NIST 2002 evaluation task. The speedup was obtained using a special case of the product-code vector quantization in which each dimension is scalar-quantized in the construction of the discrete model. However, the speedup resulted in a drop of an absolute 1.5% in equal-error rate (EER). In this paper, our previous work is generalized to the use of subvector quantization (SVQ) in the construction of HDDM. For the same NIST 2002 SV task, the use of SVQ leads to an overall speedup by a factor of 8–25 with no significant loss in EER performance.

Chat with Paper

AI Agents for this Paper