Word graph rescoring using confidence measures
نویسندگان
چکیده
This paper presents a novel approach to using con dence scores for word graph rescoring. For each word in the system's vocabulary, we computed the probability that the observation is correct given its acoustic score. Afterwards, we used these probabilities for rescoring word graphs outputted by the recognizer. We will present some implementation details as well as accuracy improvements obtained using this method.
منابع مشابه
Word Graph Rescoring Using Con dence Measures
This paper presents a novel approach to using con dence scores for word graph rescoring. For each word in the system's vocabulary, we computed the probability that the observation is correct given its acoustic score. Afterwards, we used these probabilities for rescoring word graphs outputted by the recognizer. We will present some implementation details as well as accuracy improvements obtained...
متن کاملImproved speech recognition using iterative decoding based on confidence measures
In this paper, a decoding method incorporating word-level conndence measures for improved speech recognition is presented. At rst, we focus on the estimation of conndence measures from the word graph and evaluate them in word graph rescoring (2nd-pass in 2-pass search system). Next, we propose the lexical tree search (1st-pass in 2-pass search system) incorporating the word-level conndence meas...
متن کاملConfidence measures for spoken dialogue systems
This paper provides improved confidence assessment for detection of word-level speech recognition errors, out of domain utterances and incorrect concepts in the CU Communicator system. New features from the speech understanding component are proposed for confidence annotation at utterance and concept levels. We have considered a neural network to combine all features in each level. Using the da...
متن کاملWord-Level Confidence Estimation for Machine Translation
This article introduces and evaluates several different word-level confidence measures for machine translation. These measures provide a method for labeling each word in an automatically generated translation as correct or incorrect. All approaches to confidence estimation presented here are based on word posterior probabilities. Different concepts of word posterior probabilities as well as dif...
متن کاملOn the Use of Confidence for Statistical Decision in Dialogue Strategies
This paper describes an interpretation and decision strategy that minimizes interpretation errors and perform dialogue actions which may not depend on the hypothesized concepts only, but also on confidence of what has been recognized. The concepts introduced here are applied in a system which integrates language and interpretation models into Stochastic Finite State Transducers (SFST). Furtherm...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1996