Ninth International Conference on Spoken Language Processing

Pittsburgh, PA, USA
September 17-21, 2006

Combining Phonetic Attributes Using Conditional Random Fields

Jeremy Morris, Eric Fosler-Lussier

Ohio State University, USA

A Conditional Random Field is a mathematical model for sequences that is similar in many ways to a Hidden Markov Model, but is discriminative rather than generative in nature. In this paper, we explore the application of the CRF model to ASR processing of discriminative phonetic features by building a system that performs first-pass phonetic recognition using discriminatively trained phonetic features. With this system, we show that this CRF model achieves an accuracy level in a phone recognition task that is superior to a similarly trained HMM model.

Full Paper

Bibliographic reference.  Morris, Jeremy / Fosler-Lussier, Eric (2006): "Combining phonetic attributes using conditional random fields", In INTERSPEECH-2006, paper 1287-Mon3BuP.3.