Automatic assessment of expressive oral reading

Authors:
Daniel BolañOs;Ronald A. Cole;Wayne H. Ward;Gerald A. Tindal;Paula J. Schwanenflugel;Melanie R. Kuhn
Affiliations:
Boulder Language Technologies, 2960 Center Green Court, Suite 200, Boulder, CO 80301, USA;Boulder Language Technologies, 2960 Center Green Court, Suite 200, Boulder, CO 80301, USA;Boulder Language Technologies, 2960 Center Green Court, Suite 200, Boulder, CO 80301, USA and University of Colorado at Boulder, Boulder, CO 80309, USA;University of Oregon, Eugene, OR 97403-5267, USA;The University of Georgia, Athens, GA 30602, USA;Boston University, Boston, MA 02215, USA
Venue:
Speech Communication
Year:
2013

Citing 8
Cited 0

The nature of statistical learning theory

The nature of statistical learning theory
Gene Selection for Cancer Classification using Support Vector Machines

Machine Learning
Automated Assessment of Oral Reading Prosody

Proceedings of the 2009 conference on Artificial Intelligence in Education: Building Learning Systems that Care: From Knowledge Representation to Affective Modelling
Using prosody to improve automatic speech recognition

Speech Communication
Displaying prosodic text to enhance expressive oral reading

Speech Communication
Two methods for assessing oral reading prosody

ACM Transactions on Speech and Language Processing (TSLP)
FLORA: Fluent oral reading assessment of children's speech

ACM Transactions on Speech and Language Processing (TSLP)
Enriching speech recognition with automatic detection of sentence boundaries and disfluencies

IEEE Transactions on Audio, Speech, and Language Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We investigated the automatic assessment of expressive children's oral reading of grade level text passages using a standardized rubric. After a careful review of the reading literature and a close examination of the rubric, we designed a novel set of prosodic and lexical features to characterize fluent expressive reading. A number of complementary sources of information were used to design the features, each of them motivated by research on different components of reading fluency. Features are connected to the child's reading rate, to the presence and number of pauses, filled-pauses and word-repetitions, the correlation between punctuation marks and pauses, the length of word groupings, syllable stress and duration and the location of pitch peaks and contours. The proposed features were evaluated on a corpus of 783 one-minute reading sessions from 313 students reading grade-leveled passages without assistance (cold unassisted reading). Experimental results show that the proposed lexical and prosodic features provide complementary information and are able to capture the characteristics of expressive reading. The results showed that on both the 2-point and the 4-point expressiveness scales, computer-generated ratings of expressiveness agreed with human raters better than the human raters agreed with each other. The results of the study suggest that automatic assessment of expressive oral reading can be combined with automatic measures of word accuracy and reading rate to produce an accurate multidimensional estimate of children's oral reading ability.