• The Journal of the Acoustical Society of Korea
• /
• v.22 no.2
• /
• pp.145-152
• /
• 2003

In this paper, assuming that the score of speech utterance is the product of HMM log likelihood and HMM weight, we propose a new method that HMM weights are adapted iteratively like the general MCE training. The proposed method adjusts HMM weights for better performance using delta coefficient defined in terms of misclassification measure. Therefore, the parameter estimation and the Viterbi algorithms of conventional 1:.um can be easily applied to the proposed model by constraining the sum of HMM weights to the number of HMMs in an HMM set. Comparing with the general segmental MCE training approach, computing time decreases by reducing the number of parameters to estimate and avoiding gradient calculation through the optimal state sequence. To evaluate the performance of HMM-based speech recognizer by weighting HMM likelihood, we perform Korean isolated digit recognition experiments. The experimental results show better performance than the MCE algorithm with state weighting.

• The KIPS Transactions:PartB
• /
• v.8B no.4
• /
• pp.335-342
• /
• 2001

본 논문은 보로노이 공간분류를 활용하여 원격탐사 영상인식을 위한 다층 신경망 분류기를제안한다. 제안된 다층 신경망 분류기는 보로노이 다각형 영역으로 클래스를 구분하며, 초평면 방정식의 계수를 오류 역전과 학습 초기의 연결 강도, 임계치 그리고 은닉층의 노드 수로 결정한다. 제안된 방법은 오류역전과 학습 알고리즘에서 임의로 정해주던 초기 정보를 사전 분석에 의해 공학적으로 결정함으로써 느린 수렴 속도와 학습실패 등의 단점을 피할 수 있는 장점이 있다. 보로노이 다이어그램에 대한 경계선의 초평면 방정식은 훈련집합의 클래스별 평균값을 구하여 Mathematica 패키지로 계산하였다. 제안된 다층 신경망에 의한 영상분류기의 인식능력을 평가하기 위하여 원격탐사 영상인식에서 자주 활용되는 최소거리 분류 방법과 최대우도 분류 방법으로 처리해서 비교한 결과, 최소거리 분류 방법은 실험화상에 대해 81.4%, 최대우도 부류기에 의한 분류는 87.8%, 제안한 방법은 92.2% 정확성을 가진 분류결과를 나타냈다.

• The Journal of the Acoustical Society of Korea
• /
• v.24 no.1
• /
• pp.58-68
• /
• 2005

In this paper, we propose a scheme to improve discriminative property in the feature compensation method for robust speech recognition under noisy environments. The estimation of noisy speech model used in existing feature compensation methods do not guarantee the computation of posterior probabilities which discriminate reliably among the Gaussian components. Estimation of Posterior probabilities is a crucial step in determining the discriminative factor of the Gaussian models, which in turn determines the intelligibility of the restored speech signals. The proposed scheme employs minimum classification error (MCE) training for estimating the parameters of the noisy speech model. For applying the MCE training, we propose to identify and determine the 'competing components' that are expected to affect the discriminative ability. The proposed method is applied to feature compensation based on parallel combined mixture model (PCMM). The performance is examined over Aurora 2.0 database and over the speech recorded inside a car during real driving conditions. The experimental results show improved recognition performance in both simulated environments and real-life conditions. The result verifies the effectiveness of the proposed scheme for increasing the performance of robust speech recognition systems.