• MALSORI
• /
• no.45
• /
• pp.117-126
• /
• 2003

Decision tree-based state tying has been proposed in recent years as the most popular approach for clustering the states of context-dependent hidden Markov model-based speech recognition. The aims of state tying is to reduce the number of free parameters and predict state probability distributions of unseen models. But, when doing state tying, the size of a decision tree is very important for word independent recognition. In this paper, we try to construct optimized decision tree based on the average of feature vectors in state pool and the number of seen modes. We observed that the proposed optimal decision tree is effective in predicting the state probability distribution of unseen models.

• Proceedings of the KSPS conference
• /
• 2002.11a
• /
• pp.197-200
• /
• 2002

In this paper, we propose a phoneme duration modeling in a speech recognition system based on disicion tree state tying. We assume that phone duration has a Gamma distribution. In a training mode, we model mean and variance of each state duration in context-independent phone model based on decision tree state tying. In a recognition mode, we get mean and variance of each context-dependent phone duration form state duration information obtaind during training mode. We make a comparative study of the proposed meth with conventinal methods. Our method results in good performance compared with conventional methods.

• Journal of Digital Convergence
• /
• v.13 no.1
• /
• pp.243-248
• /
• 2015

Recognition model is not defined when you configure a model, Been added to the model after model building awareness, Model a model of the clustering due to lack of recognition models are generated by modeling is causes the degradation of the recognition rate. In order to improve decision tree state tying modeling using parameter estimation of Bayesian method. The parameter estimation method is proposed Bayesian method to navigate through the model from the results of the decision tree based on the tying state according to the maximum probability method to determine the recognition model. According to our experiments on the simulation data generated by adding noise to clean speech, the proposed clustering method error rate reduction of 1.29% compared with baseline model, which is slightly better performance than the existing approach.

• Proceedings of the IEEK Conference
• /
• 2002.06d
• /
• pp.195-198
• /
• 2002

We propose an efficient mixture Gaussian synthesis method for decision tree based state tying that produces better context-dependent models in a short period of training time. This method makes it possible to handle mixture Gaussian HMMs in decision tree based state tying algorithm, and provides higher recognition performance compared to the conventional HMM training procedure using decision tree based state tying on single Gaussian GMMs. This method also reduces the steps of HMM training procedure. We applied this method to training of PBS, and we expect to achieve a little point improvement in phoneme accuarcy and reduction in training time.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.6
• /
• pp.167-176
• /
• 2005

This paper describes how the state tying model based on the decision tree which is one of Acoustic models used for speech recognition optimizes the model by reducing the number of mixture Gaussians of the output probability distribution. The state tying modeling uses a finite set of questions which is possible to include the phonological knowledge and the likelihood based decision criteria. And the recognition rate can be improved by increasing the number of mixture Gaussians of the output probability distribution. In this paper, we'll reduce the number of mixture Gaussians at the highest point of recognition rate by clustering the Gaussians. Bhattacharyya and Euclidean method will be used for the distance measure needed when clustering. And after calculating the mean and variance between the pair of lowest distance, the new Gaussians are created. The parameters for the new Gaussians are derived from the parameters of the Gaussians from which it is born. Experiments have been performed using the STOCKNAME (1,680) databases. And the test results show that the proposed method using Bhattacharyya distance measure maintains their recognition rate at $97.2\%$ and reduces the ratio of the number of mixture Gaussians by $1.0\%$. And the method using Euclidean distance measure shows that it maintains the recognition rate at $96.9\%$ and reduces the ratio of the number of mixture Gaussians by $1.0\%$. Then the methods can optimize the state tying model.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06e
• /
• pp.377-380
• /
• 1998

HMM 기반의 음성 인식기를 구현하는데 있어서 모델의 복잡도와 제한된 훈련 데이터 사이의 균형을 유지하는 것은 중요한 문제이다. 중간규모 또는 대용량 어휘 인식 시스템은 정교한 모델을 얻기 위해서 문맥종속 음소 모델링이 필수적이다. 그러나, 제한된 훈련 데이터로는 발생 가능한 모든 context를 포함하기가 어렵고, 더구나 훈련 데이터에서 관찰된 context중에서도 그 관찰빈도가 낮은 것이 많아서 신뢰성 있는 문맥종속 모델들을 얻기에는 여전히 어려움이 따른다. 또한 경우에 따라서는 계산량의 감축을 위하여 모델 규모를 축소시킬 필요도 생긴다. 이러한 문제를 해결하기 위해 본 논문에서는 unit reduction 방법들과 state tying을 이용한 방법들의 성능을 실험을 통해 비교한다. 고립단어 인식 실험결과 state tying을 이용한 방법이 unit reduction에 비하여 우수함을 확인 할 수 있었다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.4
• /
• pp.722-727
• /
• 2009

The technology of distinguishing human motion states is required in the areas of measuring and analyzing biosignals changing according to physical activities, diagnosing sleep disorder, screening the effect of treatment, examining chronic patients' kinetic state, prescribing exercise therapy, etc. The present study implemented a fuzzy inference system based on fuzzy rules that distinguish human motion states (tying, sitting, walking, and running) by acquiring and processing data of LAA, TAA, L-MAD, and T-MAD using ADXL202AE of Analog Devices embedded in an armband. The membership degree and fuzzy rules in each area of input (LAA, TAA, L-MAD, and T-MAD) and output (tying, sitting, walking, and running) data used here were determined using numeric data obtained from experiment. In the results of analyzing data for simulation generated in order of tying$\rightarrow$walking$\rightarrow$running$\rightarrow$tying, the sorting rate for motion states tying, sitting, walking, and running was 100% for each motion.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.6
• /
• pp.49-56
• /
• 1999

In many continuous speech recognition systems based on HMMs, decision tree-based state tying has been used for not only improving the robustness and accuracy of context dependent acoustic modeling but also synthesizing unseen models. To construct the phonetic decision tree, standard method performs one-level pruning using just single Gaussian triphone models. In this paper, two novel approaches, two-level decision tree and multi-mixture decision tree, are proposed to get better performance through more accurate acoustic modeling. Two-level decision tree performs two level pruning for the state tying and the mixture weight tying. Using the second level, the tied states can have different mixture weights based on the similarities in their phonetic contexts. In the second approach, phonetic decision tree continues to be updated with training sequence, mixture splitting and re-estimation. Multi-mixture Gaussian as well as single Gaussian models are used to construct the multi-mixture decision tree. Continuous speech recognition experiment using these approaches on BN-96 and WSJ5k data showed a reduction in word error rate comparing to the standard decision tree based system given similar number of tied states.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.11a
• /
• pp.17-20
• /
• 2003

본 논문에서는 공유 모델링의 대표적인 방법인 결정트리 기반 상태공유 모델을 기반으로 하여 그 출력 확률 분포의 혼합 가우시안 수를 줄임으로써 모델을 최적화하고자 하였다. 결정트리 기반의 상태공유 모델링은 일반적인 방법을 따랐으며 혼합 가우시안 수를 늘려 인식률이 최대가 되는 지점에서 혼합 가우시안을 클러스터링하여 그 수를 줄였다. 클러스터링 시에 필요한 거리 측정 방법이나 가까운 두 가우시안의 합성 방법을 여러 기법을 실험하였다. 이때 인식률은 클러스터링 이전인 97.2%를 유지하였으며 총 혼합 가우시안의 감소율은 1.0%를 보임으로써 모델을 최적화할 수 있었다.

• Journal of Korea Multimedia Society
• /
• v.13 no.3
• /
• pp.369-377
• /
• 2010

In vocabulary recognition systems based on HMM(Hidden Markov Model)s, training process unseen model bring on show a low recognition rate. If recognition vocabulary modify and make an addition then recreated modeling of executed database collected and training sequence on account of bring on additional expenses and take more time. This study suggest efficient context dependent process modeling method using decision tree-based state tying. On study suggest method is reduce recreated of model and it's offered that robustness and accuracy of context dependent acoustic modeling. Also reduce amount of model and offered training process unseen model as concerns context dependent a likely phoneme model has been used unseen model solve the matter. System performance as a result of represent vocabulary dependence recognition rate of 98.01%, vocabulary independence recognition rate of 97.38%.