Robust Spoken Language Understanding
- Robust Speech Understanding
- Error-Corrective Language Model Adaptation is an adaptation framework with error handling method to improve accuracy of speech recognition and performance of spoken language applications. The proposed error corrective language model adaptation approach exploits domain-specific language variations and recognition environment characteristics to provide robustness and adaptability for a spoken language system.
- Adaptation framework
- Channel Modeling with Fertility : Capturing channel characteristics with word-to-word substitution model and word fertility model, MLE for substitution model and Several discounting methods (absolute, Good-Turing, Kneser-Ney)
- Exploiting Linguistic Knowledge in Language Model Adaptation using whole-sentence exponential models (including MCMC sampling, Gaussian prior smoothing)
- ECLM adaptation is MAP process:
- Semantic Frame Extractor is to analyze the output of the speech recognition component and to assign a meaning representation that can be used by the dialogue manager. In many current spoken dialogue systems, the meaning of the utterance is derived directly from the recognized string using a ¡°semantic frame¡±.
- Procedure
- Input : Utterances
- Output: Meaningful concepts
- Linguistic feature generator selects useful syntactic, semantic, cognitive features based on POS tagging, chunking, and parsing.
- Machine learning techniques train models to represent linguistic character based Maximum Entropy models, Conditional Random Fields, and Neural Networks.
- Main goal
- Clearing ambiguity in natural language (Lexical/Sense/Structural ambiguity)
- Robust handling for ill-formed spoken input
- Contact
- Error-Corrective Language Model Adaptation is an adaptation framework with error handling method to improve accuracy of speech recognition and performance of spoken language applications. The proposed error corrective language model adaptation approach exploits domain-specific language variations and recognition environment characteristics to provide robustness and adaptability for a spoken language system.
Abstract
We are developing the robust spoken language understanding for speech dialogue system. We have been considering the robustness and flexibility to develop the language understanding models. To address these issues, we present a new language model adaptation method to recover in-complete inputs from speech recognition and a log-linear modeling approach to extract semantic concept from user¡¯s utterances. And we are working on several techniques such as linguistic processing, information extraction, structured / relational data learning or ensemble methods to develop the robust spoken language understanding.
Run TV-guide domain SLU system demo
Run TeleBanking domain SLU system demo
San 31, Hyoja-Dong, Pohang, 790-784, Korea
Phone: +82 54 279 5581 | Fax: +82 54 279 2299