Topic
Word error rate
About: Word error rate is a research topic. Over the lifetime, 11939 publications have been published within this topic receiving 298031 citations.
Papers published on a yearly basis
Papers
More filters
Patent•
02 May 2001
TL;DR: In this paper, new techniques and systems may be implemented to improve error correction in speech recognition systems, which may be used in a standard desktop environment, in a mobile environment, or in any other type of environment that can receive and/or present recognized speech.
Abstract: New techniques and systems may be implemented to improve error correction in speech recognition. These new techniques and systems may be implemented to correct errors in speech recognition systems may be used in a standard desktop environment, in a mobile environment, or in any other type of environment that can receive and/or present recognized speech.
423 citations
TL;DR: This paper presents a complete framework that starts with the extraction of various local regions of either discontinuity or homogeneity, and uses Boosting to learn a subset of feature vectors (weak hypotheses) and to combine them into one final hypothesis for each visual category.
Abstract: This paper explores the power and the limitations of weakly supervised categorization. We present a complete framework that starts with the extraction of various local regions of either discontinuity or homogeneity. A variety of local descriptors can be applied to form a set of feature vectors for each local region. Boosting is used to learn a subset of such feature vectors (weak hypotheses) and to combine them into one final hypothesis for each visual category. This combination of individual extractors and descriptors leads to recognition rates that are superior to other approaches which use only one specific extractor/descriptor setting. To explore the limitation of our system, we had to set up new, highly complex image databases that show the objects of interest at varying scales and poses, in cluttered background, and under considerable occlusion. We obtain classification results up to 81 percent ROC-equal error rate on the most complex of our databases. Our approach outperforms all comparable solutions on common databases.
422 citations
Proceedings Article•
30 Jul 2011
TL;DR: Meteor 1.3 as discussed by the authors was the first submission to the 2011 EMNLP Workshop on Statistical Machine Translation automatic evaluation metric tasks, which included improved text normalization, higher-precision paraphrase matching, and discrimination between content and function words.
Abstract: This paper describes Meteor 1.3, our submission to the 2011 EMNLP Workshop on Statistical Machine Translation automatic evaluation metric tasks. New metric features include improved text normalization, higher-precision paraphrase matching, and discrimination between content and function words. We include Ranking and Adequacy versions of the metric shown to have high correlation with human judgments of translation quality as well as a more balanced Tuning version shown to outperform BLEU in minimum error rate training for a phrase-based Urdu-English system.
414 citations
01 Dec 1998
TL;DR: A SVM -based face recognition algorithm that is compared with a principal component analysis (PCA) based algorithm on a difficult set of images from the FERET database and generated a similarity metric between faces that is learned from examples of differences between faces.
Abstract: Face recognition is a K class problem. where K is the number of known individuals; and support vector machines (SVMs) are a binary classification method. By reformulating the face recognition problem and reinterpreting the output of the SVM classifier. we developed a SVM -based face recognition algorithm. The face recognition problem is formulated as a problem in difference space. which models dissimilarities between two facial images. In difference space we formulate face recognition as a two class problem. The classes are: dissimilarities between faces of the same person. and dissimilarities between faces of different people. By modifying the interpretation of the decision surface generated by SVM. we generated a similarity metric between faces that is learned from examples of differences between faces. The SVM-based algorithm is compared with a principal component analysis (PCA) based algorithm on a difficult set of images from the FERET database. Performance was measured for both verification and identification scenarios. The identification performance for SVM is 77-78% versus 54% for PCA. For verification. the equal error rate is 7% for SVM and 13% for PCA.
412 citations
TL;DR: A translation model that is based on bilingual phrases to explicitly model the local context is presented and it is shown that this model performs better than the single-word based model.
Abstract: This paper is based on the work carried out in the framework of the VERBMOBIL project, which is a limited-domain speech translation task (German-English). In the final evaluation, the statistical approach was found to perform best among five competing approaches.In this paper, we will further investigate the used statistical translation models. A shortcoming of the single-word based model is that it does not take contextual information into account for the translation decisions. We will present a translation model that is based on bilingual phrases to explicitly model the local context. We will show that this model performs better than the single-word based model. We will compare monotone and non-monotone search for this model and we will investigate the benefit of using the sum criterion instead of the maximum approximation.
408 citations