Background model based posterior probability for measuring confidence
نویسندگان
چکیده
Word posterior probability (WPP) computed over LVCSR word graphs has been used successfully in measuring confidence of speech recognition output. However, for certain applications the word graph is too sparse to warrant reliable WPP estimation. In this paper, we incorporate subword units as background models to generate a subword graph for estimating posterior probability. Experiments on both English and Chinese databases show that syllable background models can repopulate the dynamic hypothesis space for effective computation of confidence measure. The resultant posterior probability confidence measure achieves 94.3% and 95.2% Out-Of-Vocabulary (OOV) word detection / rejection in English and Chinese, respectively. Correspondingly, confidence error rates are at 6.0% and 6.4%, respectively.
منابع مشابه
Measuring Hospital Performance Using Mortality Rates: An Alternative to the RAMR
Background The risk-adjusted mortality rate (RAMR) is used widely by healthcare agencies to evaluate hospital performance. The RAMR is insensitive to case volume and requires a confidence interval for proper interpretation, which results in a hypothesis testing framework. Unfamiliarity with hypothesis testing can lead to erroneous interpretations by the public and other stakeholders. We argue t...
متن کاملExact maximum coverage probabilities of confidence intervals with increasing bounds for Poisson distribution mean
A Poisson distribution is well used as a standard model for analyzing count data. So the Poisson distribution parameter estimation is widely applied in practice. Providing accurate confidence intervals for the discrete distribution parameters is very difficult. So far, many asymptotic confidence intervals for the mean of Poisson distribution is provided. It is known that the coverag...
متن کاملGeneralized Word Posterior Probability (gwpp) for Measuring Reliability of Recognized Words
To measure the reliability of recognized words in an ASR, we propose a generalized word posterior probability (GWPP) as the sole confidence measure. This measure is computed efficiently via a word graph with the forwardbackward algorithm or directly with the generalized string likelihoods of N-best strings from the recognizer. The GWPP is a modified word posterior probability where a word event...
متن کاملImage Segmentation using Gaussian Mixture Model
Abstract: Stochastic models such as mixture models, graphical models, Markov random fields and hidden Markov models have key role in probabilistic data analysis. In this paper, we used Gaussian mixture model to the pixels of an image. The parameters of the model were estimated by EM-algorithm. In addition pixel labeling corresponded to each pixel of true image was made by Bayes rule. In fact,...
متن کاملComparison of Confidence Measures for Face Recognition
This paper compares different confidence measures for the results of statistical face recognition systems. The main applications of a confidence measure are rejection of unknown people and the detection of recognition errors. Some of the confidence measures are based on the posterior probability and some on the ranking of the recognition results. The posterior probability is calculated by apply...
متن کامل