Estimation of Acoustic Microphone Vocal Tract Parameters from Throat Microphone Recordings

Joint processing of throat and acoustic microphone recordings has been an attractive tool for robust speech processing. As the throat microphones record the acoustic sounds in the form of vibrations from skin-attached sensors, they are more robust and highly correlated with the acoustic speech signal. We investigate the correlation of throat and acoustic microphone recordings. We propose a hidden Markov model (HMM)-based structure to build a mapping between throat and acoustic microphone vocal track parameters. The HMM-based estimator can be used to estimate clean acoustic speech features from noisy acoustic and throat microphone recordings. Experimental results on acoustic speech feature estimation are provided.