Paper Info
Title
Automatic pronunciation verification of english letter-names for early literacy assessment of preliterate children
Abstract
Children need to master reading letter-names and letter-sounds before reading phrases and sentences. Pronunciation assessment of letter-names and letter-sounds read aloud is an important component of preliterate children's education, and automating this process can have several advantages. The goal of this work was to automatically verify letter-names spoken by kindergarteners and first graders in realistic classroom noise conditions. We applied the same techniques developed in our previous work on automatic letter-sound verification by comparing and optimizing different acoustic models, dictionaries, and decoding grammars. Our final system was unbiased with respect to the child's grade, age, and native language and achieved 93.1% agreement (0.813 kappa agreement) with human evaluators, who agreed among themselves 95.4% of the time (0.891 kappa).
Year
DOI
Venue
2009
10.1109/ICASSP.2009.4960720
ICASSP
Keywords
Field
DocType
automatic pronunciation verification,native language,different acoustic model,automatic letter-sound verification,final system,kappa agreement,preliterate child,decoding grammar,english letter-names,human evaluator,previous work,early literacy assessment,important component,decoding,decision support systems,data mining,speech recognition,dictionaries,acoustic noise,probability density function
Pronunciation,Rule-based machine translation,Kappa,Early literacy,Computer science,Decision support system,Speech recognition,Natural language processing,Artificial intelligence,Decoding methods,First language
Conference
ISSN
Citations 
PageRank 
1520-6149
3
0.41
References 
Authors
4
5
Name
Order
Citations
PageRank
Matthew P. Black119213.67
Joseph Tepperman2738.59
Abe Kazemzadeh395752.95
Sungbok Lee4139484.13
Narayanan Shrikanth55558439.23