5th International Conference on Spoken Language Processing
We present two different approaches for robust estimation of the parameters of context-dependent hidden Markov models (HMMs) for speech recognition. The first approach, the Gaussian Merging-Splitting (GMS) algorithm, uses Gaussian splitting to uniformly distribute the Gaussians in acoustic space, and merging so as to compute only those Gaussians that have enough data for robust estimation. We show that this method is more robust than our previous training technique. The second approach, called tied-transform HMMs, uses maximum-likelihood transformation-based acoustic adaptation algorithms to transform a small HMM to a much larger HMM. Since the transforms are shared or tied among Gaussians in the larger HMM, robust estimation is achieved. We show that this approach gives a significant improvement in recognition accuracy and a dramatic reduction in memory needed to store the models.
Bibliographic reference. Sankar, Ananth (1998): "Robust HMM estimation with Gaussian merging-splitting and tied-transform HMMs", In ICSLP-1998, paper 0194.