Robust numeric recognition in spoken language dialogue
| Autor: | Mazin G. Rahim, Giuseppe Riccardi, Jerry H. Wright, Bruce Buntschuh, Allen Louis Gorin, Lawrence K. Saul |
|---|---|
| Rok vydání: | 2001 |
| Předmět: |
Linguistics and Language
Computer science business.industry Communication Speech recognition Feature extraction computer.software_genre Language and Linguistics Computer Science Applications Credit card Discriminative model Robustness (computer science) Modeling and Simulation Telephone number Computer Vision and Pattern Recognition Language model Artificial intelligence business computer Software Utterance Natural language processing Spoken language |
| Zdroj: | Speech Communication. 34:195-212 |
| ISSN: | 0167-6393 |
| DOI: | 10.1016/s0167-6393(00)00054-6 |
| Popis: | This paper addresses the problem of automatic numeric recognition and understanding in spoken language dialogue. We show that accurate numeric understanding in fluent unconstrained speech demands maintaining robustness at several different levels of system design, including acoustic, language, understanding and dialogue. We describe a robust system for numeric recognition and present algorithms for feature extraction, acoustic and language modeling, discriminative training, utterance verification and numeric understanding and validation. Experimental results from a field-trial of a spoken dialogue system are presented that include customers' responses to credit card and telephone number requests. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect