A method of speech inversion using a stochastic speech production model

摘要

We present a method that determines articulatory movements from speech acoustics using a stochastic speech production model. The model consists of HMMs (Hidden Markov Model) of articulatory movements for each phoneme and an articulatory-to-acoustic mapping for each HMM state. For a given speech acoustics, maximum a posteriori probability estimation of the articulatory parameters of the statistical model is presented. The performance on sentences was evaluated by comparing the estimated articulatory parameters with the observed parameters.