Joint versus independent phonological feature models within CRF phone recognition

Authors:
Ilana Bromberg;Jeremy Morris;Eric Fosler-Lussier
Affiliations:
The Ohio State University, Columbus, OH;The Ohio State University, Columbus, OH;The Ohio State University, Columbus, OH
Venue:
NAACL-Short '07 Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Companion Volume, Short Papers
Year:
2007

Citing 2
Cited 1

Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Feature-based pronunciation modeling for automatic speech recognition

Feature-based pronunciation modeling for automatic speech recognition

Discriminative input stream combination for conditional random field phone recognition

IEEE Transactions on Audio, Speech, and Language Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We compare the effect of joint modeling of phonological features to independent feature detectors in a Conditional Random Fields framework. Joint modeling of features is achieved by deriving phonological feature posteriors from the posterior probabilities of the phonemes. We find that joint modeling provides superior performance to the independent models on the TIMIT phone recognition task. We explore the effects of varying relationships between phonological features, and suggest that in an ASR system, phonological features should be handled as correlated, rather than independent.