• The Journal of the Acoustical Society of Korea
• /
• v.19 no.2
• /
• pp.83-89
• /
• 2000

In this paper, we proposed a discriminative adaptation method for PMC algorithm and achieved improved speech recognition rate. For the adaptation, we adopted modified PMC(MPMC) which is a variant of PMC and discriminatively adapted the association factor for each mixture of the HMM in the MPMC. From the recognition experiments, the proposed method showed better recognition rate than the conventional PMC. Also, compared with STAR algorithm which is another model parameter compensation method, the proposed method showed superior performance when the SNR is very low and the adaptation data is not sufficient.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.870-876
• /
• 1993

This paper presents a binary clustering network (BCN) and a heuristic algorithm to detect pitch for recognition of keywords in continuous speech. In order to classify nonlinear patterns, BCN separates patterns into binary clusters hierarchically and links same patterns at root level by using the supervised learning and the unsupervised learning. BCN has many desirable properties such as flexibility of dynamic structure, high classification accuracy, short learning time, and short recall time. Pitch Detection algorithm is a heuristic model that can solve the difficulties such as scaling invariance, time warping, time-shift invariance, and redundance. This recognition algorithm has shown recognition rates as high as 95% for speaker-dependent as well as multispeaker-dependent tests.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.4E
• /
• pp.28-36
• /
• 1996

In this paper, we propose a new evaluation methodology which can more clearly show the performance of the allophone modeling algorithm generally used in large vocabulary speech recognition. The proposed evaluation method shows the running characteristics and limitations of the modeling algorithm by testing how the variation of phonetic environments of training data affects the recognition performance and the desirable number of free parameters to be estimated. Using the method, we experiment results, we conclude that, in vocabulary-independent recognition task, the phonetic diversity of training data greatly affects the robustness of model, and it is necessary to develop a proper measure which can determine the number of states compromizing the robustness and the precision of the HMnet better than the conventional modeling efficiency.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.3E
• /
• pp.60-65
• /
• 1996

This paper describes on the Korean continuous speech recognition system for flight reservation. It adopts a frame-synchronous One-Pass DP search algorithm driven by syntactic constraints of context free grammar(CFG). For recognition, 48 phoneme-like units(PLU) were defined and used as basic units for acoustic modeling of Korean. This modeling was conducted using a HMM technique, where each model has 4-states 3-continuous output probability distributions and 3-discrete-duration distributions. Language modeling by CFG was also applied to the task domain of flight reservation, which consisted of 346 words and 422 rewriting rules. In the tests, the sentence recognition rate of 62.6% was obtained after speaker adaptation.

• Speech Sciences
• /
• v.7 no.4
• /
• pp.11-26
• /
• 2000

In this paper, we propose the HMM with the MIN module. Because initial and re-estimated variance vectors are important elements for performance in HMM recognition systems, we propose a method which compensates for the mismatched statistical feature of training and test data. The MIN module function is a differentiable function similar to the sigmoid function. Unlike a continuous density function, it does not include variance vectors of the data set. The proposed hybrid HMM/MIN module is a unified network in which the observation probability in the HMM is replaced by the MIN module neural network. The parameters in the unified network are re-estimated by the gradient descent method for the Maximum Likelihood (ML) criterion. In estimating parameters, the variance vector is not estimated because there is no variance element in the MIN module function. The experiment was performed to compare the performance of the proposed HMM and the conventional HMM. The experiment measured an isolated number for speaker independent recognition.

• Journal of Information Processing Systems
• /
• v.20 no.4
• /
• pp.491-500
• /
• 2024

In hopes of resolving the issue of poor quality of information input for teaching spoken English online, the study creates an English teaching assistance model based on a recognition algorithm named dynamic time warping (DTW) and relies on automated voice recognition technology. In hopes of improving the algorithm's efficiency, the study modifies the speech signal's time-domain properties during the pre-processing stage and enhances the algorithm's performance in terms of computational effort and storage space. Finally, a simulation experiment is employed to evaluate the model application's efficacy. The study's revised DTW model, which achieves recognition rates of above 95% for all phonetic symbols and tops the list for cloudy consonant recognition with rates of 98.5%, 98.8%, and 98.7% throughout the three tests, respectively, is demonstrated by the study's findings. The enhanced model for DTW voice recognition also presents higher efficiency and requires less time for training and testing. The DTW model's KS value, which is the highest among the models analyzed in the KS value analysis, is 0.63. Among the comparative models, the model also presents the lowest curve position for both test functions. This shows that the upgraded DTW model features superior voice recognition capabilities, which could significantly improve online English education and lead to better teaching outcomes.

• Journal of Korea Multimedia Society
• /
• v.5 no.5
• /
• pp.523-529
• /
• 2002

The present study describes neural networks for stereoscopic vision, which are applied to identifying human speech. In speech recognition based on stereoscopic vision neural networks (SVNN), the similarities are first obtained by comparing input vocal signals with standard models. They are then given to a dynamic process in which both competitive and cooperative processes are conducted among neighboring similarities. Through the dynamic processes, only one winner neuron is finally detected. In a comparative study, the two-layered SVNN was 7.7% higher in recognition accuracies than the hidden Markov model (HMM). From the evaluation results, it was noticed that SVNN outperformed the existing HMM recognizer.

• Journal of KIISE:Software and Applications
• /
• v.31 no.4
• /
• pp.403-410
• /
• 2004

Bimodal speech recognition systems have been proposed for enhancing recognition rate of ASR under noisy environments. Visual feature extraction is very important to develop these systems. To extract visual features, it is necessary to detect exact lip position. This paper proposed the method that detects a lip position using color similarity model and SVM. Face/Lip color distribution is teamed and the initial lip position is found by using that. The exact lip position is detected by scanning neighbor area with SVM. By experiments, it is shown that this method detects lip position exactly and fast.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.9 no.4
• /
• pp.964-969
• /
• 2008

This paper proposes a HMM-based recognition method using DMSVQ(Dynamic Multi-Section Vector Quantization) codebook by DMS(Dynamic Multi-Section) model and fuzzy concept, as a study for speaker- independent speech recognition. In this proposed recognition method, training data are divided into several dynamic section and multi-observation sequences which are given proper probabilities by fuzzy rule according to order of short distance from DMSVQ codebook per each section are obtained. Thereafter, the HMM using this multi-observation sequences is generated, and in case of recognition, a word that has the most highest probability is selected as a recognized word. Other experiments to compare with the results of recognition experiments using proposed method are implemented as a data by the various conventional recognition methods under the equivalent environment. Through the experiment results, it is proved that the proposed method in this study is superior to the conventional recognition methods.

• Journal of Digital Convergence
• /
• v.17 no.12
• /
• pp.243-248
• /
• 2019

Multi-Task Learning(MTL) is a training method that trains a single neural network with multiple tasks influences each other. In this paper, we compare performance of MTL Named entity recognition(NER) model trained with Korean traditional culture corpus and other NER model. In training process, each Bi-LSTM layer of Part of speech tagging(POS-tagging) and NER are propagated from a Bi-LSTM layer to obtain the joint loss. As a result, the MTL based Bi-LSTM model shows 1.1%~4.6% performance improvement compared to single Bi-LSTM models.