A path-stack algorithm for optimizing dynamic regimes in a statistical hidden dynamic model of speech

29 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Deep Learning: Methods and Applications (2014, background): “Subsequent work added a new hidden layer into the dynamic model to explicitly account for the target-directed, articulatory-like properties in human speech generation [45, 73, 74, 83, 96, 75, 90, 231, 232, 233, 251, 282].”
Switching Dynamic System Models for Speech Articulation and Acoustics (2004, background): “Approximate solutions have been provided for some simple versions of the the switching dynamic system model in literatures of statistics [47], speech processing [29], and of neural computation and Bayesian net [23, 34].”
Machine Learning Paradigms for Speech Recognition: An Overview (2013, methodology): “…models for ASR, a number of ML techniques invented originally in non-ASR communities, e.g. variational learning [50], pseudo-Bayesian [43], [51], Kalman filtering [32], extended Kalman filtering [39], [45], Gibbs sampling [53], orthogonal polynomial regression [34], etc., have been…”
Efficient decoding strategies for conversational speech recognition using a constrained nonlinear state-space model (2003, background): “Therefore, no path deletion is theoretically allowed during the decoding (detailed analyses can be found in [24]), which makes the search for the new model difficult.”