Local word confidence measure using word graph and n-best list
نویسندگان
چکیده
This paper presents some confidence measures for large vocabulary speech recognition which are based on word graph or N-Best List structures. More and more applications need fast estimation of any measures in order to stay real-time. We propose some simple and fast measures, locally computed, that can be directly used within the first decoding recognition process. We also define some other measures combining word graph and N-Best List. Experimental results on a French broadcast news corpus are also presented.
منابع مشابه
A Word-spotting Hypothesis Testing for Accepting/Rejecting Continuous Speech Recognition Output
The word rejection problem in speech recognition is formulated in a framework of word-spotting, where a spotted word is verified through a binary, acceptance/rejection decision. A generalized word posterior probability (GWPP), used as the sole confidence measure, is computed in a word graph, via the forward-backward algorithm or in an N-best list, using string likelihoods. The GWPP is further e...
متن کاملWord error rate minimization using an integrated confidence measure
This paper describes a new criterion of speech recognition using an integrated confidence measure for minimization of the word error rate (WER). Conventional criteria for WER minimization obtain an expected WER of a sentence hypothesis merely by comparing it with other hypotheses in an n-best list. The proposed criterion estimates the expected WER by using an integrated confidence measure with ...
متن کاملA comparison of word graph and n-best list based confidence measures
In this paper we present and compare several confidence measures for large vocabulary continuous speech recognition. We show that posterior word probabilities computed on word graphs and N-best lists clearly outperform non-probabilistic confidence measures, e.g. the acoustic stability and the hypothesis density. In addition, we prove that the estimation of posterior word probabilities on word g...
متن کاملWord level confidence measures using n-best sub-hypotheses likelihood ratio
This paper proposes an efficient confidence measure applied at the word level by combining various likelihood ratio tests. The estimates are derived from the local N-best subhypotheses. This approach allows the confidence measures to take into account the effect of neighboring words and still provides the estimate localized around the word to be verified. It produces an effective confidence mea...
متن کاملConfidence Measures for Statistical Machine Translation
In this paper, we present several confidence measures for (statistical) machine translation. We introduce word posterior probabilities for words in the target sentence that can be determined either on a word graph or on an N best list. Two alternative confidence measures that can be calculated on N best lists are proposed. The performance of the measures is evaluated on two different translatio...
متن کامل