• Proceedings of the KSPS conference
• /
• 2003.05a
• /
• pp.115-118
• /
• 2003

Channel distortion and coarticulation effect in the connected digit telephone speech make it difficult to recognize, and degrade recognition performance in the telephone environment. In this paper, as a basic research to improve the recognition performance of Korean connected digit telephone, error patterns are investigated and analyzed. Telephone digit speech database released by SITEC with HTK system is used for recognition experiments. Both DWFBA and MRTCN methods are used for feature extraction and channel compensation, respectively. Experimental results are discussed with our findings.

• Journal of the Korean Institute of Telematics and Electronics T
• /
• v.36T no.2
• /
• pp.56-62
• /
• 1999

This paper described a voice dialing system(VDS) and its hardware implementation for a speaker-dependent recognition of Korean digit speech using duty cycle. The proposed VDS consist of integrator, leveling divider circuit and recognition program. The analog speech signal is applied to the VDS through the low-pass filter cutoff frequency is 4.5(kHz). It is thoroughly confirmed that the speaker-dependent recognition of Korean digit speech is well behaved by the hardware system. Experimental results show that the recognition rate is 64% in average for Korean digit speech. Moreover, a high recognition rate of 100% is obtained for digits; /4/, /5/, /6/, /7/, /9/, /0/.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.10
• /
• pp.63-71
• /
• 2011

We present a method to modify the recognition of neural networks by the fuzzy inference in a handwritten digit recognition with large deformations, and we verified the method by the experiment. The neural networks take long time in learning and recognize 100% on the learning pattern. But the neural networks don't show a good recognition on the testing pattern. So, we apply the modified method as the fuzzy inference. As a result, the recognition and false recognition of neural networks was improved 90.2% and 9.8% respectively at 89.6% and 10.4% initially. This approach decreased especially the false recognition on digit 3, 5. We used the density of digit to extract the fuzzy membership function in this experiment. But, because the handwritten digit have varified input patterns, we will get a better recognition by extracting varifed characteristics and applying the composite fuzzy inference. We also propose the application of fuzzy inference on matching the input pattern, than applying strictly the fuzzy inference.

• MALSORI
• /
• no.44
• /
• pp.105-113
• /
• 2002

In Korean, each digit is monosyllable and some pairs are known to have high confusability, causing performance degradation of connected digit recognition systems. To improve the performance, in this paper, we employ various discriminant analyses (DA) including Linear DA (LDA), Weighted Pairwise Scatter LDA WPS-LDA), Heteroscedastic Discriminant Analysis (HDA), and Maximum Likelihood Linear Transformation (MLLT). We also examine several combinations of various DA for additional performance improvement. Experimental results show that applying any DA mentioned above improves the string accuracy, but the amount of improvement of each DA method varies according to the model complexity or number of mixtures per state. Especially, more than 20% of string error reduction is achieved by applying MLLT after WPS-LDA, compared with the baseline system, when class level of DA is defined as a tied state and 1 mixture per state is used.

• MALSORI
• /
• no.45
• /
• pp.79-91
• /
• 2003

Utterance verification aims at rejecting both out-of-vocabulary (OOV) utterances and low-confidence-scored in-vocabulary (IV) utterances. For utterance verification on Korean connected digit recognition task, we investigate several methods to construct filler and anti-digit models. In particular, we propose a substitution error correction method based on 2-best decoding results. In this method, when 1st candidate is rejected, 2nd candidate is selected if it is accepted by a specific hypothesis test, instead of simply rejecting the 1st one. Experimental results show that the proposed method outperforms the conventional log likelihood ratio (LLR) test method.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.2
• /
• pp.699-707
• /
• 2015

Although digit character recognition has got a significant improvement in recent years, it is still challenging to achieve satisfied result if the data contains an amount of distracting factors. This paper proposes a novel digit character recognition approach using a multi-layer hierarchical model, Hybrid Restricted Boltzmann Machines (HRBMs), which allows the learning architecture to be robust to background distracting factors. The insight behind the proposed model is that useful high-level features appear more frequently than distracting factors during learning, thus the high-level features can be decompose into hybrid hierarchical structures by using only small label information. In order to extract robust and compact features, a stochastic 0-1 layer is employed, which enables the model's hidden nodes to independently capture the useful character features during training. Experiments on the variations of Mixed National Institute of Standards and Technology (MNIST) dataset show that improvements of the multi-layer hierarchical model can be achieved by the proposed method. Finally, the paper shows the proposed technique which is used in a real-world application, where it is able to identify digit characters under various complex background images.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1992.06a
• /
• pp.66-70
• /
• 1992

This paper describes the simplified DTW algorithm for real time korean digit recognition and construct the digit recognition system using that algorithm. The DTW algorithm which is used nowadays have problems on real time recognition because of its massive computation. But, simplified DTW algorithm, which is proposed in this paper, solved these problems. In the case of single syllable, we use the characteristic of uniform distribution of epansion and contraction on time ais, compare distance of input pattern and reference pattern using constrainedly restricted path. As a result, we can reduce a great deal of computation and achieved that the real time korean digit recognition system.

• Journal of Internet Computing and Services
• /
• v.3 no.4
• /
• pp.51-59
• /
• 2002

For the speech recognition, this paper proposes a improved new formant tracking algorithm The recognition data for the simulation on this paper are used with the Korean digit speech. The recognition rate of the improved algorithm for the Korean digit speech shows 91% for 300 digit speech The effectiveness of this research has been confirmed through recognition simulations.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1995.06a
• /
• pp.69-72
• /
• 1995

In this paper, a new approach for Korean connected digits recognition using the spatio-temporal neural network is reported. The data of seven digits phone numbers are used in the recognition of connected words, and in the initial experiment, digit recognition rate of 28% was achieved. In this paper, to increase recognition rate, two different approaches are analyzed. In the first system, to compensate the STNN's own defect and to emphasize the Korean word's phonic characters, the starting point of phone is pointed by comparing the average magnitude and zero-crossing rate and the ending point is pointed by comparing only zero-crossing rate. The digit recoginiton rate increased to 61%. Also, in the second system, to consider fact that same word's phone is varied severally, the number of STNN's of each word is increased from one to five, and then the varied same word's phones can be included to the increased STNN's. The digit recogniton rate of connected words increased to 89%.

• Journal of KIISE:Software and Applications
• /
• v.31 no.12
• /
• pp.1581-1590
• /
• 2004

We present a robust off-line method recognizing handwritten digits by only using stroke direction codes as a feature of handwritten digits. This method makes general 8-direction codes for an input digit and then has the multi-layered neural networks learn them and recognize each digit. The 8-direction codes are made of the thinned results of each digit through SOG*(Improved Self-Organizing Graph). And the usage of these codes simplifies the complex steps processing at least two features of the existing methods. The experimental result shows that the recognition rates of this method are constantly better than 98.85% for any images in all digit databases.