Sciweavers

160 search results - page 27 / 32
» Exploiting contextual information for improved phoneme recog...
Sort
View
LREC
2008
81views Education» more  LREC 2008»
13 years 9 months ago
Speech Errors on Frequently Observed Homophones in French: Perceptual Evaluation vs Automatic Classification
The present contribution aims at increasing our understanding of automatic speech recognition (ASR) errors involving frequent homophone or almost homophone words by confronting th...
Rena Nemoto, Ioana Vasilescu, Martine Adda-Decker
EMNLP
2008
13 years 9 months ago
Modeling Annotators: A Generative Approach to Learning from Annotator Rationales
A human annotator can provide hints to a machine learner by highlighting contextual "rationales" for each of his or her annotations (Zaidan et al., 2007). How can one ex...
Omar Zaidan, Jason Eisner
JCDL
2003
ACM
231views Education» more  JCDL 2003»
14 years 26 days ago
Acquisition, Representation, Query and Analysis of Spatial Data: A Demonstration 3D Digital Library
The increasing power of techniques to model complex geometry and extract meaning from 3D information create complex data that must be described, stored, and displayed to be useful...
Jeremy Rowe, Anshuman Razdan, Arleyn Simon
SIGIR
2008
ACM
13 years 7 months ago
Classifiers without borders: incorporating fielded text from neighboring web pages
Accurate web page classification often depends crucially on information gained from neighboring pages in the local web graph. Prior work has exploited the class labels of nearby p...
Xiaoguang Qi, Brian D. Davison
CSL
2004
Springer
13 years 7 months ago
Contemporaneous text as side-information in statistical language modeling
We propose new methods to exploit contemporaneous text, such as on-line news articles, to improve language models for automatic speech recognition and other natural language proce...
Sanjeev Khudanpur, Woosung Kim