Cross-Lingual Subspace Gaussian Mixture Models for Low-Resource Speech Recognition

Abstract

This paper studies cross-lingual acoustic modeling in the context of subspace Gaussian mixture models (SGMMs). SGMMs factorize the acoustic model parameters into a set that is globally shared between all the states of a hidden Markov model (HMM) and another that is specific to the HMM states. We demonstrate that the SGMM global parameters are transferable… (More)
DOI: 10.1109/TASL.2013.2281575

20 Figures and Tables

Topics

Statistics

01020201520162017
Citations per Year

Citation Velocity: 7

Averaging 7 citations per year over the last 3 years.

Learn more about how we calculate this metric in our FAQ.
  • Presentations referencing similar topics