• Journal of Korea Multimedia Society
• /
• v.25 no.3
• /
• pp.493-501
• /
• 2022

This paper is a study on context-sensitive spelling error correction and uses the Korean WordNet (KorLex)[1] that defines the relationship between words as a graph to improve the performance of the correction[2] based on the vector information of the word embedded in the correction technique. The Korean WordNet replaced WordNet[3] developed at Princeton University in the United States and was additionally constructed for Korean. In order to learn a semantic network in graph form or to use it for learned vector information, it is necessary to transform it into a vector form by embedding learning. For transformation, we list the nodes (limited number) in a line format like a sentence in a graph in the form of a network before the training input. One of the learning techniques that use this strategy is Deepwalk[4]. DeepWalk is used to learn graphs between words in the Korean WordNet. The graph embedding information is used in concatenation with the word vector information of the learned language model for correction, and the final correction word is determined by the cosine distance value between the vectors. In this paper, In order to test whether the information of graph embedding affects the improvement of the performance of context- sensitive spelling error correction, a confused word pair was constructed and tested from the perspective of Word Sense Disambiguation(WSD). In the experimental results, the average correction performance of all confused word pairs was improved by 2.24% compared to the baseline correction performance.

• International Commerce and Information Review
• /
• v.12 no.4
• /
• pp.171-192
• /
• 2010

In general, a stock index and its individual stocks are assumed to follow a random walk. A stock index is an important source of information and one that is seen by people everyday, regardless of their investment intentions. This paper examines the correlation between the KOSPI-the index that best reflects the Korean stock market and the macro - economic variables that have been found to influence the index by previous studies. The sample period considers the years after 2000 when the Korean stock market matured as restrictions on foreign investors were removed. For this purpose, a Vector Error Correction Model (VECM) and KOSPI equation with a general pacific approach were used. This paper aims at verifying the factors that determined the KOSPI after 2000 and at examining whether there was structural change in the investment environment. It also investigates changes in the factors determining the KOSPI's performance as a result of structural changes in the investment environment. The V AR (Vector Autoregressive) model including the nine variables was selected as a baseline model whose stability was tested using the unit root test. The results from the VECM and the structural changes in the investment environment can be summarized by the following Inner story points.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.2
• /
• pp.445-452
• /
• 2010

In this paper, an attempt has been made to design the controller applicable for H.264 level3 encoder of baseline profile on full hardware basis. The designed controller module first stores the images supplied from CMOS Image Sensor(CIS) at main memory, and then reads or stores the image data in macroblock unit according to encoder operation. The timing cycle of the DMA controller required to process a macroblock is 478 cycles. In order to verify the our design, reference-C encoder, which is compatible to JM 9.4, is developed and the designed controller is verified by using the test vector generated from the reference C code. The number of cycle in the designed DMA controller is reduced by 40% compared with the cycle of using Xilinx MIG.

• MALSORI
• /
• no.60
• /
• pp.165-180
• /
• 2006

In this paper, we present several confidence measures (CM) for speech recognition systems to evaluate the reliability of recognition results. We propose heuristic CMs such as mean log-likelihood score, N-best word log-likelihood ratio, likelihood sequence fluctuation and likelihood ratio testing(LRT)-based CMs using several types of anti-models. Furthermore, we propose new algorithms to add weighting terms on phone-level log-likelihood ratio to merge word-level log-likelihood ratios. These weighting terms are computed from the distance between acoustic models and knowledge-based phoneme classifications. LRT-based CMs show better performance than heuristic CMs excessively, and LRT-based CMs using phonetic information show that the relative reduction in equal error rate ranges between $8{\sim}13%$ compared to the baseline LRT-based CMs. We use the support vector machine to fuse several CMs and improve the performance of utterance verification. From our experiments, we know that selection of CMs with low correlation is more effective than CMs with high correlation.

• Journal of Information Science Theory and Practice
• /
• v.9 no.2
• /
• pp.1-17
• /
• 2021

Pseudo relevance feedback (PRF) is a powerful query expansion (QE) technique that prepares queries using the top k pseudorelevant documents and choosing expansion elements. Traditional PRF frameworks have robustly handled vocabulary mismatch corresponding to user queries and pertinent documents; nevertheless, expansion elements are chosen, disregarding similarity to the original query's elements. Word embedding (WE) schemes comprise techniques of significant interest concerning QE, that falls within the information retrieval domain. Deep averaging networks (DANs) defines a framework relying on average word presence passed through multiple linear layers. The complete query is understandably represented using the average vector comprising the query terms. The vector may be employed for determining expansion elements pertinent to the entire query. In this study, we suggest a DANs-based technique that augments PRF frameworks by integrating WE similarities to facilitate Arabic information retrieval. The technique is based on the fundamental that the top pseudo-relevant document set is assessed to determine candidate element distribution and select expansion terms appropriately, considering their similarity to the average vector representing the initial query elements. The Word2Vec model is selected for executing the experiments on a standard Arabic TREC 2001/2002 set. The majority of the evaluations indicate that the PRF implementation in the present study offers a significant performance improvement compared to that of the baseline PRF frameworks.

• MALSORI
• /
• no.52
• /
• pp.145-160
• /
• 2004

In this paper, a new noise compensation method based on the eigenvoice framework in feature space is proposed to reduce the mismatch between training and testing environments. The difference between clean and noisy environments is represented by the linear combination of K eigenvectors that represent the variation among environments. In the proposed method, the performance improvement of speech recognition systems is largely affected by how to construct the noisy models and the bias vector set. In this paper, two methods, the one based on MAP adaptation method and the other using stereo DB, are proposed to construct the noisy models. In experiments using Aurora 2 DB, we obtained 44.86% relative improvement with eigen-environment method in comparison with baseline system. Especially, in clean condition training mode, our proposed method yielded 66.74% relative improvement, which is better performance than several methods previously proposed in Aurora project.

• ETRI Journal
• /
• v.35 no.1
• /
• pp.100-108
• /
• 2013

In this paper, a feature extraction (FE) method is proposed that is comparable to the traditional FE methods used in automatic speech recognition systems. Unlike the conventional spectral-based FE methods, the proposed method evaluates the similarities between an embedded speech signal and a set of predefined speech attractor models in the reconstructed phase space (RPS) domain. In the first step, a set of Gaussian mixture models is trained to represent the speech attractors in the RPS. Next, for a new input speech frame, a posterior-probability-based feature vector is evaluated, which represents the similarity between the embedded frame and the learned speech attractors. We conduct experiments for a speech recognition task utilizing a toolkit based on hidden Markov models, over FARSDAT, a well-known Persian speech corpus. Through the proposed FE method, we gain 3.11% absolute phoneme error rate improvement in comparison to the baseline system, which exploits the mel-frequency cepstral coefficient FE method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.6
• /
• pp.813-818
• /
• 2007

This paper is concerned with the problem of recognizing definition sentences. Given a definition question like "Who is the person X?", we are to retrieve the definition sentences which capture descriptive information correspond variously to a person's age, occupation, of some role a person played in an event from the collection of news articles. In order to retrieve as many relevant sentences for the definition question as possible, we adopt a centroid based statistical approach which has been applied in summarization of multiple documents. To improve the precision and recall performance, the weight measure of centroid words is supplemented by using external knowledge resource such as Wikipedia and redundant candidate sentences are removed from candidate definitions. We see some improvements obtained by our approach over the baseline for 20 IT persons who have high document frequency.

• Phonetics and Speech Sciences
• /
• v.6 no.1
• /
• pp.77-83
• /
• 2014

This paper proposes a speaker and environment clustering method in order to overcome the degradation of the speech recognition performance caused by various noise and speaker characteristics. In this paper, instead of using the distance between Gaussian mixture model (GMM) weight vectors as in the Google's approach, the distance between the adapted mean vectors based on the modified maximum a posteriori (MAP) adaptation is used as a distance measure for vector quantization (VQ) clustering. According to our experiments on the simulation data generated by adding noise to clean speech, the proposed clustering method yields error rate reduction of 10.6% compared with baseline speaker-independent (SI) model, which is slightly better performance than the Google's approach.

• Phonetics and Speech Sciences
• /
• v.7 no.4
• /
• pp.17-25
• /
• 2015

For blind source separation of convolutive mixtures, FDICA(Frequency Domain Independent Component Analysis) algorithms are generally used. Since FDICA algorithm such as Sawada FDICA, IVA(Independent Vector Analysis) works on the frequency bin basis with a natural gradient descent method, it takes much time to converge. In this paper, we propose a new method to improve convergence speed in FDICA algorithm. The proposed method reduces the number of iteration drastically in the process of natural gradient descent method by applying a weighted inner product constraint of unmixing matrix. Experimental results have shown that the proposed method achieved large improvement of convergence speed without degrading the separation performance of the baseline algorithms.