Robust ASR using Support Vector Machines
Speech Communication
The application of hidden Markov models in speech recognition
Foundations and Trends in Signal Processing
Invited paper: Automatic speech recognition: History, methods and challenges
Pattern Recognition
Matrix updates for perceptron training of continuous density hidden Markov models
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Training data selection for improving discriminative training of acoustic models
Pattern Recognition Letters
Discriminative training of HMMs for automatic speech recognition: A survey
Computer Speech and Language
A study on the generalization capability of acoustic models for robust speech recognition
IEEE Transactions on Audio, Speech, and Language Processing
International Journal of Speech Technology
Empirical comparisons of various discriminative language models for speech recognition
ROCLING '11 Proceedings of the 23rd Conference on Computational Linguistics and Speech Processing
Large margin mixture of AR models for time series classification
Applied Soft Computing
Affective command-based control system integrating brain signals in commands control systems
Computers in Human Behavior
Journal of Signal Processing Systems
Hi-index | 0.00 |
In this paper, motivated by large margin classifiers in machine learning, we propose a novel method to estimate continuous-density hidden Markov model (CDHMM) for speech recognition according to the principle of maximizing the minimum multiclass separation margin. The approach is named large margin HMM. First, we show this type of large margin HMM estimation problem can be formulated as a constrained minimax optimization problem. Second, we propose to solve this constrained minimax optimization problem by using a penalized gradient descent algorithm, where the original objective function, i.e., minimum margin, is approximated by a differentiable function and the constraints are cast as penalty terms in the objective function. The new training method is evaluated in the speaker-independent isolated E-set recognition and the TIDIGITS connected digit string recognition tasks. Experimental results clearly show that the large margin HMMs consistently outperform the conventional HMM training methods. It has been consistently observed that the large margin training method yields significant recognition error rate reduction even on top of some popular discriminative training methods