Statistical methods for estimation of direct and differential kinematics of the vocal tract

Authors:
Adam Lammert;Louis Goldstein;Shrikanth Narayanan;Khalil Iskarous
Affiliations:
Signal Analysis & Interpretation Laboratory (SAIL), University of Southern California, 3710 McClintock Ave., Los Angeles, CA 90089, USA1The SAIL homepage is http://sail.usc.edu.1;Department of Linguistics, University of Southern California, Grace Ford Salvatory 301, Los Angeles, CA 90089-1693, USA and Haskins Laboratories, 300 George Street, Suite 900, New Haven, CT 06511, ...;Signal Analysis & Interpretation Laboratory (SAIL), University of Southern California, 3710 McClintock Ave., Los Angeles, CA 90089, USA1The SAIL homepage is http://sail.usc.edu.1 and Department of ...;Department of Linguistics, University of Southern California, Grace Ford Salvatory 301, Los Angeles, CA 90089-1693, USA and Haskins Laboratories, 300 George Street, Suite 900, New Haven, CT 06511, ...
Venue:
Speech Communication
Year:
2013

Citing 20
Cited 0

Manipulator inverse kinematic solutions based on vector formulations and damped least-squares methods

IEEE Transactions on Systems, Man and Cybernetics
Multilayer feedforward networks are universal approximators

Neural Networks
Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Constrained supervised learning

Journal of Mathematical Psychology
The calibration index and taxonomy for robot kinematic calibration methods

International Journal of Robotics Research
Locally Weighted Learning

Artificial Intelligence Review - Special issue on lazy learning
Synthesis of V-V sequences with a 2D biomechanical tongue model controlled by the equilibrium point hypothesis

Speech Communication - Special issue on speech production: models and data
Active Appearance Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
Fundamentals of Manipulator Calibration

Fundamentals of Manipulator Calibration
A fast learning algorithm for deep belief nets

Neural Computation
Pattern Recognition and Machine Learning (Information Science and Statistics)

Pattern Recognition and Machine Learning (Information Science and Statistics)
Acoustic to articulatory parameter mapping using an assembly of neural networks

ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
Statistical mapping between articulatory movements and acoustic spectrum using a Gaussian mixture model

Speech Communication
Adaptive mixtures of local experts

Neural Computation
Operational Space Control: A Theoretical and Empirical Comparison

International Journal of Robotics Research
From acoustics to Vocal Tract time functions

ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
Improvement of the neighborhood based Levenberg-Marquardt algorithm by local adaptation of the learning coefficient

IEEE Transactions on Neural Networks
Multilayer Potts Perceptrons With Levenberg–Marquardt Learning

IEEE Transactions on Neural Networks
Training feedforward networks with the Marquardt algorithm

IEEE Transactions on Neural Networks
Articulatory Information for Noise Robust Speech Recognition

IEEE Transactions on Audio, Speech, and Language Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present and evaluate two statistical methods for estimating kinematic relationships of the speech production system: artificial neural networks and locally-weighted regression. The work is motivated by the need to characterize this motor system, with particular focus on estimating differential aspects of kinematics. Kinematic analysis will facilitate progress in a variety of areas, including the nature of speech production goals, articulatory redundancy and, relatedly, acoustic-to-articulatory inversion. Statistical methods must be used to estimate these relationships from data since they are infeasible to express in closed form. Statistical models are optimized and evaluated - using a heldout data validation procedure - on two sets of synthetic speech data. The theoretical and practical advantages of both methods are also discussed. It is shown that both direct and differential kinematics can be estimated with high accuracy, even for complex, nonlinear relationships. Locally-weighted regression displays the best overall performance, which may be due to practical advantages in its training procedure. Moreover, accurate estimation can be achieved using only a modest amount of training data, as judged by convergence of performance. The algorithms are also applied to real-time MRI data, and the results are generally consistent with those obtained from synthetic data.