Results 1 
6 of
6
LANDMARKBASED SPEECH RECOGNITION: REPORT OF THE 2004 Johns Hopkins Summer Workshop
, 2005
"... ..."
An effective algorithm for string correction using generalized edit distances  I. Description of the . . .
, 1981
"... This paper deals with the problem of estimating a transmitted string X, from the corresponding received string Y, which is a noisy version of X,. We assume that Y contains*any number of substitution, insertion, and deletion errors, and that no two consecutive symbols of X, were deleted in transmissi ..."
Abstract

Cited by 19 (11 self)
 Add to MetaCart
This paper deals with the problem of estimating a transmitted string X, from the corresponding received string Y, which is a noisy version of X,. We assume that Y contains*any number of substitution, insertion, and deletion errors, and that no two consecutive symbols of X, were deleted in transmission. We have shown that for channels which cause independent errors, and whose error probabilities exceed those of noisy strings studied in the literature [ 121, at least 99.5 % of the erroneous strings will not contain two consecutive deletion errors. The best estimate X * of X, is defined as that element of H which minimizes the generalized Levenshtein distance D ( X/Y) between X and Y. Using dynamic programming principles, an algorithm is presented which yields X+ without computing individually the distances between every word of H and Y. Though this algorithm requires more memory, it can be shown that it is, in general, computationally less complex than all other existing algorithms which perform the same task.
AN SVM FRONTEND LANDMARK SPEECH RECOGNITION SYSTEM
, 2008
"... Support vector machines (SVMs) can be trained to detect manner transitions between phones and to identify the manner and place of articulation of any given phone. The SVMs can perform these tasks with high accuracy using a variety of acoustic representations. The SVMs generalize well to unseen test ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
(Show Context)
Support vector machines (SVMs) can be trained to detect manner transitions between phones and to identify the manner and place of articulation of any given phone. The SVMs can perform these tasks with high accuracy using a variety of acoustic representations. The SVMs generalize well to unseen test data if these data were created under identical conditions to the training corpus. Unseen acoustic data from different corpora present a problem for the SVM, even if these acoustic data were generated under similar conditions. The discriminant outputs of these SVMs are used to create both a hybrid SVM/HMM (hidden Markov model) phone recognition system and a hybrid SVM/HMM word recognition system. There is a significant improvement in both phone and word recognition accuracy when these SVM discriminant features are used instead of mel frequency cepstral coefficients (MFCCs).
SVMHMM LANDMARK BASED SPEECH RECOGNITION
, 2009
"... Support vector machines (SVMs) are trained to detect acousticphonetic landmarks, and to identify both the manner and place of articulation of the phones producing each landmark with high accuracy. The discriminant outputs of these SVMs are used as input features for a standard HMM based ASR system. ..."
Abstract
 Add to MetaCart
(Show Context)
Support vector machines (SVMs) are trained to detect acousticphonetic landmarks, and to identify both the manner and place of articulation of the phones producing each landmark with high accuracy. The discriminant outputs of these SVMs are used as input features for a standard HMM based ASR system. There is a significant improvement in both the phone and word recognition accuracy when using these SVM discriminant features when compared to the phone and word recognition accuracy of an MFCC based recognizer.
© Pattern Recognition Society. THE USE OF CONTEXT IN PATTERN RECOGNITION*'t"
, 1977
"... Abstract The importance of contextual information, at various different levels, for the satisfactory solution of pattern recognition problems is illustrated by examples. A tutorial survey of techniques for using contextual information in pattern recognition is presented. Emphasis is placed on the p ..."
Abstract
 Add to MetaCart
Abstract The importance of contextual information, at various different levels, for the satisfactory solution of pattern recognition problems is illustrated by examples. A tutorial survey of techniques for using contextual information in pattern recognition is presented. Emphasis is placed on the problems of image classification and text recognition, where the text is in the form of machine and handprinted characters, cursive script, and speech. The related problems of scene analysis, natural language understanding, and errorcorrecting compilers are only lightly touched upon. Character recognition Speech recognition Pattern recognition correction Spelling correction Image classification language understanding Context Artificial intelligence
An Effective Algorithm for String Cowection Using Generaliied Edit Distances II. Computational Complexity of the Algorithm and Some Applications*
"... This paper deals with the problem of estimating an unknown transmitted string X, belonging to a finite dictionary H from its observable noisy version Y. In the first part of this paper [IS] we have developed an algorithm, referred to as ~go~t ~ I, to find the string Xi fH which minimizes the general ..."
Abstract
 Add to MetaCart
(Show Context)
This paper deals with the problem of estimating an unknown transmitted string X, belonging to a finite dictionary H from its observable noisy version Y. In the first part of this paper [IS] we have developed an algorithm, referred to as ~go~t ~ I, to find the string Xi fH which minimizes the generalized Levenshtein distance D ( X,/Y). In this part of the paper we study the computations complexity of Algorithm I, and illustrate qu~titatively the advantage Algorithm I has over the standard technique and other algorithms. Its superiority has been shown for various dictionaries, including the one consisting of the 102 1 most common English words of length greater than unity [23]. A comparison between Algorithm I and other algorithms used to correct misspelled words of a regular language is also made here. Some applications of Algorithm I are also discussed. I.