Stochastic trajectory modeling for speech recognition
Y Gong, JP Haton - Proceedings of ICASSP'94. IEEE …, 1994 - ieeexplore.ieee.org
Models observations of phoneme-based speech units as clusters of trajectories in their
parameter space. The trajectories are modeled by a mixture of state sequences of multi …
parameter space. The trajectories are modeled by a mixture of state sequences of multi …
Parametric trajectory models for speech recognition
The basic motivation for employing trajectory models for speech recognition is that
sequences of speech features are statistically dependent and that the effective and efficient …
sequences of speech features are statistically dependent and that the effective and efficient …
Gaussian mixture models of phonetic boundaries for speech recognition
MK Omar, M Hasegawa-Johnson… - IEEE Workshop on …, 2001 - ieeexplore.ieee.org
A new approach to represent temporal correlation in an automatic speech recognition
system is described. It introduces an acoustic feature set that captures the dynamics of a …
system is described. It introduces an acoustic feature set that captures the dynamics of a …
Tree-based state clustering for large vocabulary speech recognition
JJ Odell, PC Woodland… - Proceedings of ICSIPNN'94 …, 1994 - ieeexplore.ieee.org
The key problem to be faced when building a HMM-based continuous speech recogniser is
maintaining the balance between model complexity and available training data. For large …
maintaining the balance between model complexity and available training data. For large …
Pitch dependent phone modelling for HMM based speech recognition
H Singer, S Sagayama - [Proceedings] ICASSP-92: 1992 IEEE …, 1992 - ieeexplore.ieee.org
The authors propose a novel method of incorporating pitch information into a hidden Markov
model (HMM) phoneme recognizer by exploiting the correlation between pitch and spectral …
model (HMM) phoneme recognizer by exploiting the correlation between pitch and spectral …
Context modeling with the stochastic segment model
M Ostendorf, I Bechwati… - [Proceedings] ICASSP-92 …, 1992 - ieeexplore.ieee.org
The authors describe an approach, the stochastic segment model, for context modeling in
continuous speech recognition for models based on multivariate Gaussian distributions …
continuous speech recognition for models based on multivariate Gaussian distributions …
Linear dynamic segmental HMMs: Variability representation and training procedure
WJ Holmes, MJ Russell - 1997 IEEE International Conference …, 1997 - ieeexplore.ieee.org
This paper describes investigations into the use of linear dynamic segmental hidden Markov
models (SHMMs) for modelling speech feature-vector trajectories and their associated …
models (SHMMs) for modelling speech feature-vector trajectories and their associated …
Structured Markov models for speech recognition
F Wolfertstetter, G Ruske - 1995 International Conference on …, 1995 - ieeexplore.ieee.org
This paper proposes a new modeling of the structure of speech units as a graph consisting
of base functions and a transition network. A cluster algorithm taking into account the actual …
of base functions and a transition network. A cluster algorithm taking into account the actual …
Phonetic recognition in a segment-based HMM
JN Marcus - 1993 IEEE International Conference on Acoustics …, 1993 - ieeexplore.ieee.org
The author describes a segment-based HMM (hidden Markov model) recognizer and
presents phonetic recognition results achieved with the system. As opposed to a …
presents phonetic recognition results achieved with the system. As opposed to a …
A segmental speech model with applications to word spotting
The authors present a segmental speech model that explicitly models the dynamics in a
variable-duration speech segment by using a time-varying trajectory model of the speech …
variable-duration speech segment by using a time-varying trajectory model of the speech …