• Communications of Mathematical Education
• /
• v.23 no.3
• /
• pp.599-624
• /
• 2009

The purpose of this study was to investigate the relationship between error types and Polya's problem solving process. For doing this, we selected 106 sophomore students in a middle school and gave them algebra word problem test. With this test, we analyzed the students' error types in solving algebra word problems. First, We analyzed students' errors in solving algebra word problems into the following six error types. The result showed that the rate of student's errors in each type is as follows: "misinterpreted language"(39.7%), "distorted theorem or solution"(38.2%), "technical error"(11.8%), "unverified solution"(7.4%), "misused data"(2.9%) and "logically invalid inference"(0%). Therefore, we found that the most of student's errors occur in "misinterpreted language" and "distorted theorem or solution" types. According to the analysis of the relationship between students' error types and Polya's problem-solving process, we found that students who made errors of "misinterpreted language" and "distorted theorem or solution" types had some problems in the stage of "understanding", "planning" and "looking back". Also those who made errors of "unverified solution" type showed some problems in "planing" and "looking back" steps. Finally, errors of "misused data" and "technical error" types were related in "carrying out" and "looking back" steps, respectively.

• Journal of Broadcast Engineering
• /
• v.16 no.2
• /
• pp.207-215
• /
• 2011

A signal passed through multi-path channel suffers ISI(Inter-Symbol Interference) and severe distortions caused by channel delay spread and noise components at the SC-FDE(Single Carrier with Frequency Domain Equalizer) transmission. Conventional UW(Unique-Word) based SC-FDE iterative channel estimation improves channel estimation performance by smoothing estimated CIR(Channel Impulse Response) of the noise components outside the channel length at time domain and restoring the broken cyclic property through UW reconstruction. In this paper, we propose channel estimation scheme through noise suppression within channel length. To suppress the noise, we estimate noise standard deviation as estimated CIR of the noise components outside the channel length and make criteria of the noise standard deviation gain that doesn't affect the original signal samples. When estimated CIR samples within channel length are less than the criteria value using the noise standard deviation and gain, the noise components are removed. Simulation results show that the proposed channel estimation scheme brings good channel MSE(Mean Square Error) and good BER(Bit Error Rate) performance.

• The Journal of the Korea Contents Association
• /
• v.6 no.1
• /
• pp.80-84
• /
• 2006

Motivated by the fact that cluster reduction strategies such as inserting a vowel or deleting a consonant in resolving English complex clusters differ depending on studies, this paper investigates the repair strategies employed by Korean EFL students. A total of 60 college students participated in the present study and the participants' production of English voiceless word-initial and word-final clusters was measured using the materials designed for this study. It has been shown that prosodic positions such as onset and coda and the number of cluster sequences influenced cluster reduction strategies. The error rates of both insertion and deletion were noticeably higher in the coda position than in the onset position and both insertion and deletion error rates were higher in triconsonatal cluster than in biconsonantal cluster sequences. Overall, the insertion rate was higher than the deletion rate. However, the deletion rate was significantly higher than the insertion rate in triconsonantal coda cluster sequences. Because of this, the deletion rate was higher than the insertion rate for triconsonantal cluster sequences across onset and coda. Also, the high deletion rate of triconsonantal coda clusters contributed to the high deletion rate for the coda clusters in general.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.2
• /
• pp.131-136
• /
• 2020

Wake Up Word (WUW) is a short utterance used to convert speech recognizer to recognition mode. The WUW defined by the user who actually use the speech recognizer is called user-defined WUW. In this paper, to recognize user-defined WUW, we construct traditional Gaussian Mixture Model-Hidden Markov Model (GMM-HMM), Linear Discriminant Analysis (LDA)-GMM-HMM and LDA-Deep Neural Network (DNN)-HMM based system and compare their performances. Also, to improve recognition accuracy of the WUW system, a threshold method is applied to each model, which significantly reduces the error rate of the WUW recognition and the rejection failure rate of non-WUW simultaneously. For LDA-DNN-HMM system, when the WUW error rate is 9.84 %, the rejection failure rate of non-WUW is 0.0058 %, which is about 4.82 times lower than the LDA-GMM-HMM system. These results demonstrate that LDA-DNN-HMM model developed in this paper proves to be highly effective for constructing user-defined WUW recognition system.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.335-341
• /
• 2022

In this paper, we adopt a transformer that shows remarkable performance in natural language processing as an acoustic model of hybrid speech recognition. The transformer acoustic model uses attention structures to process sequential data and shows high performance with low computational cost. This paper proposes a method to improve the performance of transformer AM by applying each of the four algorithms of sequence discriminative training, a weighted finite-state transducer (wFST)-based learning used in the existing DNN-HMM model. In addition, compared to the Cross Entropy (CE) learning method, sequence discriminative method shows 5 % of the relative Word Error Rate (WER).

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.145-150
• /
• 2020

최근 음성인식 분야에서 신경망 기반의 종단간 모델이 제안되고 있다. 해당 모델들은 음성을 직접 입력받아 전사된 문장을 생성한다. 음성을 직접 입력받는 모델의 특성상 데이터의 품질이 모델의 성능에 많은 영향을 준다. 본 논문에서는 이러한 종단간 모델의 문제점을 해결하고자 음성인식 결과를 후처리하기 위한 멀티모달 기반 모델을 제안한다. 제안 모델은 음성과 전사된 문장을 입력 받는다. 입력된 각각의 데이터는 Encoder를 통해 자질을 추출하고 주의집중 메커니즘을 통해 Decoder로 추출된 정보를 전달한다. Decoder에서는 전달받은 주의집중 메커니즘의 결과를 바탕으로 후처리된 토큰을 생성한다. 본 논문에서는 후처리 모델의 성능을 평가하기 위해 word error rate를 사용했으며, 실험결과 Google cloud speech to text모델에 비해 word error rate가 8% 감소한 것을 확인했다.

• Phonetics and Speech Sciences
• /
• v.10 no.3
• /
• pp.31-39
• /
• 2018

This paper aims to present a taxonomy of non-standard words (NSW) for developing a French text normalization system and to propose a method for evaluating this system based on a corpus. The proposed taxonomy of French NSWs consists of 13 categories, including 2 types of letter-based categories and 9 types of number-based categories. In order to evaluate the text normalization system, a representative test set including NSWs from various text domains, such as news, literature, non-fiction, social-networking services (SNSs), and transcriptions, is constructed, and an evaluation equation is proposed reflecting the distribution of the NSW categories of the target domain to which the system is applied. The error rate of the test set is 1.64%, while the error rate of the whole corpus is 2.08%, reflecting the NSW distribution in the corpus. The results show that the literature and SNS domains are assessed as having higher error rates compared to the test set.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.5
• /
• pp.765-776
• /
• 1995

This paper describes a speaker adaptation method to improve the recognition performance of MLP(multiLayer Perceptron) based HMM(Hidden Markov Model) speech recognizer. In this method, we use lst-order linear transformation network to fit data of a new speaker to the MLP. Transformation parameters are adjusted by back-propagating classification error to the transformation network while leaving the MLP classifier fixed. The recognition system is based on semicontinuous HMM's which use the MLP as a fuzzy vector quantizer. The experimental results show that rapid speaker adaptation resulting in high recognition performance can be accomplished by this method. Namely, for supervised adaptation, the error rate is signifecantly reduced from 9.2% for the baseline system to 5.6% after speaker adaptation. And for unsupervised adaptation, the error rate is reduced to 5.1%, without any information from new speakers.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.4
• /
• pp.127-136
• /
• 2023

Many research results on the traffic enforcement of illegal driving of twowheeled motor vehicles using license plate recognition are introduced. Deep learning convolutional neural networks can be used for character and word recognition of license plates because of better generalization capability compared to traditional Backpropagation neural networks. In the plates of twowheeled motor vehicles, the interdependent government and city words are included. If we implement the mutually independent word recognizers using error correction rules for two word recognition results, efficient license plate recognition results can be derived. The CPU based convolutional neural network without library under real time processing has an advantage of low cost real application compared to GPU based convolutional neural network with library. In this paper twowheeled motor vehicle license plate recognition algorithm is introduced using CPU based deep-learning convolutional neural network. The experimental results show that the proposed plate recognizer has 96.2% success rate for outdoor twowheeled motor vehicle images in real time.

• Phonetics and Speech Sciences
• /
• v.6 no.3
• /
• pp.155-164
• /
• 2014

This paper proposes a new method to determine the recognition units for large vocabulary continuous speech recognition (LVCSR) in Korean by applying unsupervised segmentation and merging. In the proposed method, a text sentence is segmented into morphemes and position information is added to morphemes. Then submorpheme units are obtained by splitting the morpheme units through the maximization of posterior probability terms. The posterior probability terms are computed from the morpheme frequency distribution, the morpheme length distribution, and the morpheme frequency-of-frequency distribution. Finally, the recognition units are obtained by sequentially merging the submorpheme pair with the highest frequency. Computer experiments are conducted using a Korean LVCSR with a 100k word vocabulary and a trigram language model obtained by a 300 million eojeol (word phrase) corpus. The proposed method is shown to reduce the out-of-vocabulary rate to 1.8% and reduce the syllable error rate relatively by 14.0%.