The Ordinate testing system uses speech processing technology that was built to handle the different rhythms and varied pronunciations used by native and non-native English speakers. The system generates scores based on the exact words used in the spoken responses, as well as the pace, fluency, and pronunciation of those words in phrases and sentences. In addition to recognizing the words uttered, the system also aligns the speech signal, i.e., it locates the part of signal containing relevant segments, syllables, and words.

Base measures are then derived from the linguistic units (segments, syllables, words), based on statistical models of native speakers. The base measures are combined into four diagnostic sub-scores using advanced statistical modeling techniques. Two of the diagnostic sub-scores are based on the content of what is spoken, and two are based on the manner in which the responses are spoken. An Overall Score is calculated as a weighted combination of the diagnostic sub-scores.

For the Versant for English test, responses to four item tasks are currently used for automated scoring. These are: reading aloud, repeating sentences, building sentences, and giving short answers to questions. In scoring, there is exactly one correct word sequence expected for each response to the Reading and Repeat items. Expert judgment was used to define correct answers to the short-answer question and sentence-build items. Most of the short-answer and some of the sentence-build items have multiple answers that are accepted as correct. All short-answer questions were pre-tested on diverse samples of native and non-native speakers. All items retained in the item banks were answered correctly by at least 90% of the native sample.