iVector
Also known as: Identity Vector, i-vector
A low-dimensional representation of voice characteristics widely used in speaker recognition and verification systems. iVectors capture many acoustic aspects of a speaker's voice in a compact form, making them useful for automatically estimating speech intelligibility in people with disordered speech. By analyzing iVectors, systems can predict how well automatic speech recognition will perform for a given speaker, helping clinicians determine appropriate assistive technology interventions.
Category: speech recognition · machine learning · natural language processing · assessment
Related: Automatic Speech Recognition · Speech Intelligibility · Disordered Speech · Machine Learning