Overview Downloads  Publications Performance Collaboration
DPM Inference for Acoustic Modeling
Home Buttons

Mission:

Nonparametric Bayesian models have become increasingly popular in speech recognition for their ability to discover data’s underlying structure in an iterative manner. Dirichlet process mixtures (DPMs) are a widely used nonparametric method that do not require a priori assumptions about the structure of the data. DPMs, however, require an infinite number of parameters so inference algorithms are needed to make posterior calculations tractable. The focus of this work is an evaluation of three variational inference algorithms for acoustic modeling: Accelerated Variational Dirichlet Process Mixtures (AVDPM), Collapsed Variational Stick Breaking (CVSB), and Collapsed Dirichlet Priors (CDP). Phoneme classification is performed as a simple task to assess the viability of these algorithms for larger speech recognition applications.


Finding Clusters
EX: A set of data is generated from multiple distributions but it might not be clear how many.
  What's New:
  • (4/7/2013): Began construction on website.

Overview: Learn more about DPMs, variational inference, and the experimental setup used in this work.

Downloads: Find relevant scripts, data, and information used in this work.

Publications: Access background information related to this project.

Performance: A quick look at the overall performance of the variational inference algorithms used in this work.

Footer

Up | Home | Courses | Projects | Proposals | Publications
Please direct questions or comments to joseph.picone@gmail.com