Retrieving Tract Variables From Acoustics: A Comparison of Different Machine Learning Strategies

Vikramjit Mitra, Hosung Nam, Carol Y. Espy-Wilson, Elliot Saltzman, Louis Goldstein
2010 IEEE Journal on Selected Topics in Signal Processing  
Many different studies have claimed that articulatory information can be used to improve the performance of automatic speech recognition systems. Unfortunately, such articulatory information is not readily available in typical speaker-listener situations. Consequently, such information has to be estimated from the acoustic signal in a process which is usually termed "speech-inversion." This study aims to propose and compare various machine learning strategies for speech inversion: Trajectory
more » ... ture density networks (TMDNs), feedforward artificial neural networks ( FF-ANN), support vector regression (SVR), autoregressive artificial neural network (AR-ANN), and distal supervised learning (DSL). Further, using a database generated by the Haskins Laboratories speech production model, we test the claim that information regarding constrictions produced by the distinct organs of the vocal tract (vocal tract variables) is superior to flesh-point information (articulatory pellet trajectories) for the inversion process. Index Terms-Articulatory phonology, articulatory speech recognition (ASR), artificial neural networks (ANNs), coarticulation, distal supervised learning, mixture density networks, speech inversion, task dynamic and applications model, vocal-tract variables.
doi:10.1109/jstsp.2010.2076013 pmid:23326297 pmcid:PMC3544523 fatcat:ahhhv3juojc6hpke2zmxhnxg5m