Corrective models for speech recognition of inflected languages

Authors:
Izhak Shafran;Keith Hall
Affiliations:
Johns Hopkins University, Baltimore, MD;Johns Hopkins University, Baltimore, MD
Venue:
EMNLP '06 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing
Year:
2006

Citing 8
Cited 5

A hierarchical duration model for speech recognition based on the ANGIE framework

Speech Communication
A Comparative Study on Feature Selection in Text Categorization

ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning
Tagging inflective languages: prediction of morphological categories for a rich, structured tagset

COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
Attention shifting for parsing speech

ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Coarse-to-fine n-best parsing and MaxEnt discriminative reranking

ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Discriminative syntactic language modeling for speech recognition

ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Speech recognition of Czech: inclusion of rare words helps

ACLstudent '05 Proceedings of the ACL Student Research Workshop
Edit-distance of weighted automata

CIAA'02 Proceedings of the 7th international conference on Implementation and application of automata

Morph-based speech recognition and modeling of out-of-vocabulary words across languages

ACM Transactions on Speech and Language Processing (TSLP)
Information retrieval test collection for searching spontaneous Czech speech

TSD'07 Proceedings of the 10th international conference on Text, speech and dialogue
Improved recognition of spontaneous Hungarian speech: morphological and acoustic modeling techniques for a less resourced task

IEEE Transactions on Audio, Speech, and Language Processing
Efficient training of discriminative language models by sample selection

Speech Communication
Overview of the CLEF-2006 cross-language speech retrieval track

CLEF'06 Proceedings of the 7th international conference on Cross-Language Evaluation Forum: evaluation of multilingual and multi-modal information retrieval

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a corrective model for speech recognition of inflected languages. The model, based on a discriminative framework, incorporates word n-grams features as well as factored morphological features, providing error reduction over the model based solely on word n-gram features. Experiments on a large vocabulary task, namely the Czech portion of the MALACH corpus, demonstrate performance gain of about 1.1--1.5% absolute in word error rate, wherein morphological features contribute about a third of the improvement. A simple feature selection mechanism based on X2 statistics is shown to be effective in reducing the number of features by about 70% without any loss in performance, making it feasible to explore yet larger feature spaces.