Estimating articulatory motion from speech wave
Speech Communication - Special issue: Speech research in Japan
Competitive learning algorithms for vector quantization
Neural Networks
Low-dimensional phoneme mapping using a continuity constraint
Low-dimensional phoneme mapping using a continuity constraint
Articulatory-to-acoustic mapping for inverse problem
Speech Communication
Production models as a structural basis for automatic speech recognition
Speech Communication - Special issue on speech production: models and data
Quantitative association of vocal-tract and facial behavior
Speech Communication - Special issue on auditory-visual speech processing
The Geometry of Algorithms with Orthogonality Constraints
SIAM Journal on Matrix Analysis and Applications
Linear Prediction of Speech
Physiologically Based Speech Synthesis
Advances in Neural Information Processing Systems 5, [NIPS Conference]
Machine-learning methods for inferring vocal-tract articulation from speech acoustics
Machine-learning methods for inferring vocal-tract articulation from speech acoustics
Visualizing speech with a recurrent neural network trained on human acoustic-articulatory data
Visualizing speech with a recurrent neural network trained on human acoustic-articulatory data
Data-driven production models for speech processing
Data-driven production models for speech processing
Understanding Digital Signal Processing (2nd Edition)
Understanding Digital Signal Processing (2nd Edition)
Production-Oriented Models for Speech Recognition
IEICE - Transactions on Information and Systems
ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 01
The HDM: a segmental hidden dynamic model of coarticulation
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
Editorial note: Bridging the gap between human and automatic speech recognition
Speech Communication
A blind algorithm for recovering articulator positions from acoustics
Asilomar'09 Proceedings of the 43rd Asilomar conference on Signals, systems and computers
Using articulatory likelihoods in the recognition of dysarthric speech
Speech Communication
Hi-index | 0.00 |
Motor theories, which postulate that speech perception is related to linguistically significant movements of the vocal tract, have guided speech perception research for nearly four decades but have had little impact on automatic speech recognition. In this paper, we describe a signal processing technique named MIMICRI that may help link motor theory with automatic speech recognition by providing a practical approach to recovering articulator positions from acoustics. MIMICRI's name reflects three important operations it can perform on time-series data: it can reduce the dimensionality of a data set (manifold inference); it can blindly invert nonlinear functions applied to the data (mapping inversion); and it can use temporal context to estimate intermediate data (contextual recovery of information). In order for MIMICRI to work, the signals to be analyzed must be functions of unobservable signals that lie on a linear subspace of the set of all unobservable signals. For example, MIMICRI will typically work if the unobservable signals are band-pass and we know the pass-band, as is the case for articulator motions. We discuss the abilities of MIMICRI as they relate to speech processing applications, particularly as they relate to inverting the mapping from speech articulator positions to acoustics. We then present a mathematical proof that explains why MIMICRI can invert nonlinear functions, which it can do even in some cases in which the mapping from the unobservable variables to the observable variables is many-to-one. Finally, we show that MIMICRI is able to infer accurately the positions of the speech articulators from speech acoustics for vowels. Five parameters estimated by MIMICRI were more linearly related to articulator positions than 128 spectral energies.