A Rough Guide to the Acoustic-to-articulatory Inversion of Speech

| This article reviews a speci c speech research area called acoustic-to-articulatory inversion of speech, or speech inversion, which refers to the problem of mapping the acoustic speech signal onto a space describing the conguration of the human vocal tract that actually produced this signal. This space may be modeled in a variety of ways, such as with trajectories of the movement of the articulators certain parts of the human vocal tractderived by means of some specialized medical imaging device, or by using linguistics-related abstract classes to describe the evolution of the articulatory state through time. The problem is by far non-trivial, mainly due to the one-to-many nature and the high non-linearity of the acoustic to articulatory mapping. Numerous approaches towards its solution have been proposed. Such a solution could have several applications, with most important the probability of improving the performance of current automatic speech recognition systems. Keywords|Acoustic-to-Articulatory Inversion, Detection of Phonological Features, Speech Recognition, Machine