ISCA Archive Eurospeech 1997
ISCA Archive Eurospeech 1997

Modeling dependency in adaptation of acoustic models using multiscale tree processes

Ashvin Kannan, Mari Ostendorf

To adapt the large number of parameters in a speech recognition acoustic model with a small amount of data, some notion of parameter dependence is needed. We present a dependence model to relate parameters in a parsimonious framework using a Gaussian multiscale process defined by the evolution of a linear stochastic dynamical system on a tree. To adapt all classes from all adaptation data, we formulate adaptation as optimal smoothing of the tree process. This approach is used to adapt two types of models: Gaussians, and Gaussian processes (segment models) characterized by a polynomial mean trajectory. Recognition results presented on the Switchboard corpus show improvements in supervised and unsupervised modes.