Patterns of durational variation were examined by applying 15 previously published rhythm measures to a large corpus of speech from five languages. In order to achieve consistent segmentation across all languages, an automatic speech recognition system was developed to divide the waveforms into consonantal and vocalic regions. The resulting duration measurements rest strictly on acoustic criteria. Machine classification showed that rhythm measures could separate languages at rates above chance. Within-language variability in rhythm measures, however, was large and comparable to that between languages. Therefore, different languages could not be identified reliably from single paragraphs. In experiments separating pairs of languages, a rhythm measure that was relatively successful at separating one pair often performed very poorly on another pair: there was no broadly successful rhythm measure. Separation of all five languages at once required a combination of three rhythm measures. Many triplets were about equally effective, but the confusion patterns between languages varied with the choice of rhythm measures.

Automated scoring systems used for the evaluation of spoken or written responses in language assessments need to balance good empirical performance with the interpretability of the scoring models. We compare several methods of feature selection for such scoring systems and show that the use of shrinkage methods such as Lasso regression makes it possible to rapidly build models that both satisfy the requirements of validity and intepretability, crucial in assessment contexts as well as achieve good empirical performance.

This research report provides an overview of the R&D efforts at Educational Testing Service related to its capability for automated scoring of nonnative spontaneous speech with the SpeechRaterSM automated scoring service since its initial version was deployed in 2006. While most aspects of this R&D work have been published in various venues in recent years, no comprehensive account of the current state of SpeechRater has been provided since the initial publications following its first operational use in 2006. After a brief review of recent related work by other institutions, we summarize the main features and feature classes that have been developed and introduced into SpeechRater in the past 10 years, including features measuring aspects of pronunciation, prosody, vocabulary, grammar, content, and discourse. Furthermore, new types of filtering models for flagging nonscorable spoken responses are described, as is our new hybrid way of building linear regression scoring models with improved feature selection. Finally, empirical results for SpeechRater 5.0 (operationally deployed in 2016) are provided.

This paper is a preliminary report on using text complexity measurement in the service of a new educational application. We describe a reading intervention where a child takes turns reading a book aloud with a virtual reading partner. Our ultimate goal is to provide meaningful feedback to the parent or the teacher by continuously tracking the child's improvement in reading fluency. We show that this would not be a simple endeavor, due to an intricate relationship between text complexity from the point of view of comprehension and reading rate.

Automated scoring of written and spoken responses is an NLP application that can significantly impact lives especially when deployed as part of high-stakes tests such as the GRE® and the TOEFL®. Ethical considerations require that automated scoring algorithms treat all testtakers fairly. The educational measurement community has done significant research on fairness in assessments and automated scoring systems must incorporate their recommendations. The best way to do that is by making available automated, non-proprietary tools to NLP researchers that directly incorporate these recommendations and generate the analyses needed to help identify and resolve biases in their scoring systems. In this paper, we attempt to provide such a solution.