Syntactic features for Arabic speech recognition

We report word error rate improvements with syntactic features using a neural probabilistic language model through N-best re-scoring. The syntactic features we use include exposed head words and their non-terminal labels both before and after the predicted word. Neural network LMs generalize better...

Full description

Saved in:
Bibliographic Details
Main Authors: Kuo, H.-K.J., Mangu, L., Emami, A., Zitouni, I., Young-Suk Lee
Format: Conference Proceeding
Language:English
Subjects:
Broadcasting
Context modeling
Decoding
Error analysis
Feature extraction
Natural languages
Neural networks
Predictive models
Speech recognition
Testing
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We report word error rate improvements with syntactic features using a neural probabilistic language model through N-best re-scoring. The syntactic features we use include exposed head words and their non-terminal labels both before and after the predicted word. Neural network LMs generalize better to unseen events by modeling words and other context features in continuous space. They are suitable for incorporating many different types of features, including syntactic features, where there is no pre-defined back-off order. We choose an N-best re-scoring framework to be able to take full advantage of the complete parse tree of the entire sentence. Using syntactic features, along with morphological features, improves the word error rate (WER) by up to 5.5% relative, from 9.4% to 8.6%, on the latest GALE evaluation test set.
DOI:10.1109/ASRU.2009.5373470