Predictive speaker adaptation in speech recognition
S Cox - Computer Speech & Language, 1995 - Elsevier
A major problem with most speaker adaptation schemes is that they rely on the speaker
providing at least one example of each acoustic unit (word, phone, triphone, etc.) in the …
providing at least one example of each acoustic unit (word, phone, triphone, etc.) in the …
On automatic speech recognition at the dawn of the 21st century
CH Lee - IEICE TRANSACTIONS on Information and Systems, 2003 - search.ieice.org
In the last three decades of the 20th Century, research in speech recognition has been
intensively carried out worldwide, spurred on by advances in signal processing, algorithms …
intensively carried out worldwide, spurred on by advances in signal processing, algorithms …
[PDF][PDF] HMM-based speech synthesis and its applications
T Masuko - Institute of Technology, 2002 - Citeseer
This thesis describes a novel approach to text-to-speech synthesis (TTS) based on hidden
Markov model (HMM). There have been several attempts proposed to utilize HMM for …
Markov model (HMM). There have been several attempts proposed to utilize HMM for …
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 …
Rapid signer adaptation for continuous sign language recognition using a combined approach of eigenvoices, MLLR, and MAP
U Von Agris, C Blomer, KF Kraiss - 2008 19th International …, 2008 - ieeexplore.ieee.org
Current sign language recognition systems are still designed for signer-dependent
operation only and thus suffer from the problem of interpersonal variability in production …
operation only and thus suffer from the problem of interpersonal variability in production …
Speaker adaptation using combined transformation and Bayesian methods
V Digalakis, L Neumeyer - 1995 International Conference on …, 1995 - ieeexplore.ieee.org
The performance and robustness of a speech recognition system can be improved by
adapting the speech models to the speaker, the channel and the task. In continuous mixture …
adapting the speech models to the speaker, the channel and the task. In continuous mixture …
Environment adaptation for robust speaker verification by cascading maximum likelihood linear regression and reinforced learning
In speaker verification over public telephone networks, utterances can be obtained from
different types of handsets. Different handsets may introduce different degrees of distortion …
different types of handsets. Different handsets may introduce different degrees of distortion …
[PDF][PDF] Robust speech recognition in noise: an evaluation using the spine corpus
JHL Hansen, R Sarikaya, U Yapanel… - … Conference on Speech …, 2001 - researchgate.net
In this paper, methodologies for effective speech recognition are considered along with
evaluations of an NRL speech in noise corpus entitled SPINE. When speech is produced in …
evaluations of an NRL speech in noise corpus entitled SPINE. When speech is produced in …
[PDF][PDF] Impact of variabilities on speech recognition
Major progress is being recorded regularly on both the technology and exploitation of
Automatic Speech Recognition (ASR) and spoken language systems. However, there are …
Automatic Speech Recognition (ASR) and spoken language systems. However, there are …
Vector-field-smoothed Bayesian learning for incremental speaker adaptation
J Takahashi, S Sagayama - 1995 International Conference on …, 1995 - ieeexplore.ieee.org
The paper presents a fast and incremental speaker adaptation method called MAP/VFS,
which combines maximum a posteriori (MAP) estimation, or in other words Bayesian …
which combines maximum a posteriori (MAP) estimation, or in other words Bayesian …