Combining Knowledge Sourcesto Reorder N - Best Speech Hypothesis
نویسندگان
چکیده
A simple and general method is described that can combine diierent knowledge sources to reorder N-best lists of hypotheses produced by a speech recognizer. The method is automatically trainable, acquiring information from both positive and negative examples. In experiments, the method was tested on a 1000-utterance sample of unseen ATIS data.
منابع مشابه
Combining Knowledge Sources to Reorder N-Best Speech Hypothesis Lists
A simple and general method is described that can combine different knowledge sources to reorder N-best lists of hypotheses produced by a speech recognizer. The method is automatically trainable, acquiring information from both positive and negative examples. In experiments, the method was tested on a 1000-utterance sample of unseen ATIS data. 1. I N T R O D U C T I O N During the last few year...
متن کاملUsing Knowledge-Based Scores for Identifying Best Speech Recognition Hypothesis
The paper presents the evaluation of a knowledge-based scoring method applied to the problem of identifying the best speech recognition hypothesis (SRH) in a functioning multimodal dialogue system. The competing SRHs are evaluated in terms of their semantic coherence using the high-level domain knowledge encoded in the ontology. We conducted an annotation experiment and showed that humans can r...
متن کاملIs N-Best Dead?
We developed a faster search algorithm that avoids the use of the N-Best paradigm until after more powerful knowledge sources have been used. We found, however, that there was little or no decrease in word errors. We then showed that the use of the N-Best paradigm is still essential for the use of still more powerful knowledge sources, and for several other purposes that are outlined in the pap...
متن کاملEmpirically combining unnormalized NNLM and back-off N-gram for fast N-best rescoring in speech recognition
Neural network language models (NNLM) have been proved to be quite powerful for sequence modeling, including feed-forward NNLM (FNNLM), recurrent NNLM (RNNLM), etc. One main issue concerned for NNLM is the heavy computational burden of the output layer, where the output needs to be probabilistically normalized and the normalizing factors require lots of computation. How to fast rescore the N-be...
متن کاملInformations morpho-syntaxiques et adaptation thématique pour améliorer la reconnaissance de la parole
A way to improve outputs produced by automatic speech recognition (ASR) systems isto integrate additional linguistic knowledge. Our research in this eld focuses on two aspects:morpho-syntactic information and thematic adaptation.In the rst part, we propose a new mode of integration of parts of speech in a post-processingstage of speech decoding. To do this, we tag N-best sentenc...
متن کامل