Fundamentals of speech recognition
Fundamentals of speech recognition
A comparison of novel techniques for rapid speaker adaptation
Speech Communication
Speaker Adaptive Training: A Maximum Likelihood Approach to Speaker Normalization
ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97)-Volume 2 - Volume 2
Experiments in Speaker Normalisation and Adaptation for Large Vocabulary Speech Recognition
ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97)-Volume 2 - Volume 2
A parametric approach to vocal tract length normalization
ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 01
A vector Taylor series approach for environment-independent speech recognition
ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 02
Refinement Approach for Adaptation Based on Combination of MAP and fMLLR
TSD '09 Proceedings of the 12th International Conference on Text, Speech and Dialogue
Predictor-corrector adaptation by using time evolution system with macroscopic time scale
IEEE Transactions on Audio, Speech, and Language Processing
A Maximum Likelihood Approach to Continuous Speech Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
A study on speaker adaptation of the parameters of continuousdensity hidden Markov models
IEEE Transactions on Signal Processing
IEEE Transactions on Audio, Speech, and Language Processing
| Hi-index | 0.00 |
The purpose of this paper is to describe the development of a speaker adaptation method that improves speech recognition performance regardless of the amount of adaptation data. For that purpose, we propose the consistent employment of a maximum a posteriori (MAP)-based Bayesian estimation for both feature space normalization and model space adaptation. Namely, constrained structural maximum a posteriori linear regression (CSMAPLR) is first performed in a feature space to compensate for the speaker characteristics, and then, SMAPLR is performed in a model space to capture the remaining speaker characteristics. A prior distribution stabilizes the parameter estimation especially when the amount of adaptation data is small. In the proposed method, CSMAPLR and SMAPLR are performed based on the same acoustic model. Therefore, the dimension-dependent variations of feature and model spaces can be similar. Dimension-dependent variations of the transformation matrix are explained well by the prior distribution. Therefore, by sharing the same prior distribution between CSMAPLR and SMAPLR, their parameter estimations can be appropriately regularized in both spaces. Experiments on large vocabulary continuous speech recognition using the Corpus of Spontaneous Japanese (CSJ) and the MIT OpenCourseWare corpus (MIT-OCW) confirm the effectiveness of the proposed method compared with other conventional adaptation methods with and without using speaker adaptive training.