Class-based n-gram models of natural language
Computational Linguistics
Improving Generalization with Active Learning
Machine Learning - Special issue on structured connectionist systems
Inducing Features of Random Fields
IEEE Transactions on Pattern Analysis and Machine Intelligence
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Information Retrieval Techniques for Speech Applications [this book is based on the workshop “Information Retrieval Techniques for Speech Applications”, held as part of the 24th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in New Orleans, USA, in September 2001].
The mathematics of statistical machine translation: parameter estimation
Computational Linguistics - Special issue on using large corpora: II
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
Open-domain voice-activated question answering
COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
Statistical phrase-based translation
NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
An improved error model for noisy channel spelling correction
ACL '00 Proceedings of the 38th Annual Meeting on Association for Computational Linguistics
A comparison of algorithms for maximum entropy parameter estimation
COLING-02 proceedings of the 6th conference on Natural language learning - Volume 20
Discriminative Reranking for Natural Language Parsing
Computational Linguistics
Error correction via a post-processor for continuous speech recognition
ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 01
SAICSIT '10 Proceedings of the 2010 Annual Research Conference of the South African Institute of Computer Scientists and Information Technologists
Enabling accent resilient speech based information retrieval
Proceedings of the 21st international conference companion on World Wide Web
Hi-index | 0.00 |
The main issues of practical spoken-language applications forhuman-computer interface are how to overcome speech recognitionerrors and guarantee the reasonable end-performance ofspoken-language applications. Therefore, handling the erroneouslyrecognized outputs is a key in developing robust spoken-languagesystems. To address this problem, we present a method to improvethe accuracy of speech recognition and performance ofspoken-language applications. The proposed error correctivereranking approach exploits recognition environment characteristicsand domain-specific semantic information to provide robustness andadaptability for a spoken-language system. We demonstrate someexperiments of spoken dialogue tasks and empirical results thatshow an improvement in accuracy for both speech recognition andspoken-language understanding. In our experiment, we show an errorreduction of up to 9.7% and 16.8%; of word error rate, and 5.5% and7.9% of understanding error for the air travel and telebankingservice domains.