Assessment of Communicative Features in Automated Speech Systems
Description
Those learning a second language often undergo proficiency examinations or tests performed by human evaluators. These examinations are intended to allow the speech of the learner to be assessed and, in some systems, scored by the human evaluator using various criteria, such as fluency, to determine the learner’s proficiency such as the Test of English as a Second Language (TOEFL) administered by Education Testing Service of Princeton, New Jersey. This technology relates to a speech processing program that applies automatic speech recognition (ASR) knowledge and acoustic and experimental phonetics. The system analyzes speech to create an automated score to predict the degree of nativeness or intelligibility of pronunciation and provide an accurate evaluation of a speaker’s communicative abilities.
Additional Information
Patent number and inventors
9,947,322
Okim Kang and David Johnson.
Potential applications
Educational testing and automated speech interpretation applications.
Benefits and advantages
Text-based independent models and systems such as this one use unstructured monologues from the speaker during assessment. Where the systems can accurately use the prosody of the speech to improve recognition of the words spoken, the models created and used by the systems can also accurately assess and provide feedback to a non-native language speaker.
Case number and licensing status
2013-018
This invention is available for licensing.