Results 1 
7 of
7
Semantic Confidence Measurement for Spoken Dialogue Systems
 IEEE Trans. on SAP
, 2005
"... Abstract—This paper proposes two methods to incorporate semantic information into word and concept level confidence measurement. The first method uses tag and extension probabilities obtained from a statistical classer and parser. The second method uses a maximum entropy based semantic structured la ..."
Abstract

Cited by 12 (0 self)
 Add to MetaCart
Abstract—This paper proposes two methods to incorporate semantic information into word and concept level confidence measurement. The first method uses tag and extension probabilities obtained from a statistical classer and parser. The second method uses a maximum entropy based semantic structured language model to assign probabilities to each word. Incorporation of semantic features into a lattice posterior probability based confidence measure provides significant improvements compared to posterior probability when used together in an air travel reservation task. At 5% False Alarm (FA) rate relative improvements of 28 % and 61 % in Correct Acceptance (CA) rate are achieved for word level and concept level confidence measurements, respectively. I.
Statistical Modelling in Continuous Speech Recognition (CSR)
 IN CONFERENCE ON UNCERTAINTY IN ARTIFICIAL INTELLIGENCE
, 2001
"... Automatic continuous speech recognition (CSR) is sufficiently ..."
Abstract

Cited by 11 (1 self)
 Add to MetaCart
Automatic continuous speech recognition (CSR) is sufficiently
HMMS AND RELATED SPEECH RECOGNITION TECHNOLOGIES
 SPRINGER HANDBOOK ON SPEECH PROCESSING AND SPEECH COMMUNICATION 1
"... Almost all present day continuous speech recognition (CSR) systems are based on Hidden Markov Models (HMMs). Although the fundamentals of HMMbased CSR have been understood for several decades, there has been steady progress in refining the technology both in terms of reducing the impact of the inhe ..."
Abstract

Cited by 7 (0 self)
 Add to MetaCart
Almost all present day continuous speech recognition (CSR) systems are based on Hidden Markov Models (HMMs). Although the fundamentals of HMMbased CSR have been understood for several decades, there has been steady progress in refining the technology both in terms of reducing the impact of the inherent assumptions, and in adapting the models for specific applications and environments. The aim of this chapter is to review the core architecture of a HMMbased CSR system and then outline the major areas of refinement incorporated into modernday systems.
Bayes risk minimization using metric loss functions
 In Proceedings of the European Conference on Speech Communication and Technology, Interspeech
, 2005
"... In this work, fundamental properties of Bayes decision rule using general loss functions are derived analytically and are verified experimentally for automatic speech recognition. It is shown that, for maximum posterior probabilities larger than 1/2, Bayes decision rule with a metric loss function a ..."
Abstract

Cited by 6 (1 self)
 Add to MetaCart
(Show Context)
In this work, fundamental properties of Bayes decision rule using general loss functions are derived analytically and are verified experimentally for automatic speech recognition. It is shown that, for maximum posterior probabilities larger than 1/2, Bayes decision rule with a metric loss function always decides on the posterior maximizing class independent of the specific choice of (metric) loss function. Also for maximum posterior probabilities less than 1/2, a condition is derived under which the Bayes risk using a general metric loss function is still minimized by the posterior maximizing class. For a speech recognition task with low initial word error rate, it is shown that nearly 2/3 of the test utterances fulfil these conditions and need not be considered for Bayes risk minimization with Levenshtein loss, which reduces the computational complexity of Bayes risk minimization. In addition, bounds for the difference between the Bayes risk for the posterior maximizing class and minimum Bayes risk are derived, which can serve as cost estimates for Bayes risk minimization approaches. 1.
INTERSPEECH 2010 On the relation of Bayes Risk, Word Error, and Word Posteriors in ASR
"... In automatic speech recognition, we are faced with a wellknown inconsistency: Bayes decision rule is usually used to minimize sentence (word sequence) error, whereas in practice we want to minimize word error, which also is the usual evaluation measure. Recently, a number of speech recognition appro ..."
Abstract
 Add to MetaCart
(Show Context)
In automatic speech recognition, we are faced with a wellknown inconsistency: Bayes decision rule is usually used to minimize sentence (word sequence) error, whereas in practice we want to minimize word error, which also is the usual evaluation measure. Recently, a number of speech recognition approaches to approximate Bayes decision rule with word error (Levenshtein/edit distance) cost were proposed. Nevertheless, experiments show that the decisions often remain the same and that the effect on the word error rate is limited, especially at low error rates. In this work, further analytic evidence for these observations is provided. A set of conditions is presented, for which Bayes decision rule with sentence and word error cost function leads to the same decisions. Furthermore, the case of word error cost is investigated and related to word posterior probabilities. The analytic results are verified experimentally on several large vocabulary speech recognition tasks. 1.
Bayes Risk Minimization using Metric Loss Functions
"... In this work, fundamental properties of Bayes decision rule using general loss functions are derived analytically and are verified experimentally for automatic speech recognition. It is shown that, for maximum posterior probabilities larger than 1/2, Bayes decision rule with a metric loss function a ..."
Abstract
 Add to MetaCart
(Show Context)
In this work, fundamental properties of Bayes decision rule using general loss functions are derived analytically and are verified experimentally for automatic speech recognition. It is shown that, for maximum posterior probabilities larger than 1/2, Bayes decision rule with a metric loss function always decides on the posterior maximizing class independent of the specific choice of (metric) loss function. Also for maximum posterior probabilities less than 1/2, a condition is derived under which the Bayes risk using a general metric loss function is still minimized by the posterior maximizing class. For a speech recognition task with low initial word error rate, it is shown that nearly 2/3 of the test utterances fulfil these conditions and need not be considered for Bayes risk minimization with Levenshtein loss, which reduces the computational complexity of Bayes risk minimization. In addition, bounds for the difference between the Bayes risk for the posterior maximizing class and minimum Bayes risk are derived, which can serve as cost estimates for Bayes risk minimization approaches. 1.
Application of the ITCirst spoken dialog system in a medical domain
, 2002
"... The paper describes the ITCirst approach for handling spoken dialog interactions over the telephone network. We will specifically describe the usage of the dialog system within a telemedicine application scenario. ..."
Abstract
 Add to MetaCart
The paper describes the ITCirst approach for handling spoken dialog interactions over the telephone network. We will specifically describe the usage of the dialog system within a telemedicine application scenario.