• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.3 s.303
• /
• pp.115-120
• /
• 2005

In this paper, we propose a new robust content-based musical genre classification algorithm using multi-feature clustering(MFC) method. In contrast to previous works, this paper focuses on two practical issues of the system dependency problem on different input query patterns(or portions) and input query lengths which causes serious uncertainty of the system performance. In order to solve these problems, a new approach called multi-feature clustering(MFC) based on k-means clustering is proposed. To verify the performance of the proposed method, several excerpts with variable duration were extracted from every other position in a queried music file. Effectiveness of the system with MFC and without MFC is compared in terms of the classification accuracy. It is demonstrated that the use of MFC significantly improves the system stability of musical genre classification performance with higher accuracy rate.

• Journal of Korean Institute of Industrial Engineers
• /
• v.20 no.1
• /
• pp.99-112
• /
• 1994

This paper describe the development of a systematic method of slicing solid parts based on a data structure called Sliced Profile Data Structure(SPDS). SPDS is an augmented polygon data structure that allows multiple layers of sliced profiles to be connected together. The method consists of five steps: (1) Selection of slicing directions, (2) Determination of slicing levels, (3) Creation of sliced profiles, (4) Connection of sliced profiles, and (5) Refinement. The presented method is aimed at enhancing the applicability of CSG for manufacturing by overcoming the problem of non-uniqueness and global nature. The SPDS-based method of feature extraction is suitable for recognizing broad scope of features with detailed information. The method is also suitable for identifying the global relationships among features and is capable of incorporating the context dependency of feature extraction.

• Phonetics and Speech Sciences
• /
• v.6 no.4
• /
• pp.127-132
• /
• 2014

This paper describes a robust speech recognition technique by reconstructing spectral components mismatched with a training environment. Although the cluster-based reconstruction method can compensate the unreliable components from reliable components in the same spectral vector by assuming an independent, identically distributed Gaussian-mixture process of training spectral vectors, the presented method exploits the temporal dependency of speech to reconstruct the components by introducing a hidden-Markov-model prior which incorporates an internal state transition plausible for an observed spectral vector sequence. The experimental results indicate that the described method can provide temporally consistent reconstruction and further improve recognition performance on average compared to the conventional method.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.3
• /
• pp.11-20
• /
• 2006

This paper describes the technique which utilizes a fuzzy neural network to sketch feature extraction in digital images. We configure an artificial neural network and make it learn fuzzy membership functions to decide a local threshold applying to sketch feature extraction. To do this. we put the learning data which is membership functions generated based on optimal feature map of a few standard images into the artificial neural network. The proposed technique extracts sketch features in an images very effectively and rapidly because the input fuzzy variable have some desirable characteristics for feature extraction such as dependency of local intensity and excellent performance and the proposed fuzzy neural network is learned from their membership functions, We show that the fuzzy neural network has a good performance in extracting sketch features without human intervention.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2007.11a
• /
• pp.405-414
• /
• 2007

This paper describes a preliminary work on prosody modeling aspect of a text-to-speech system for Thai. Specifically, the model is designed to predict symbolic markers from text (i.e., prosodic phrase boundaries, accent, and intonation boundaries), and then using these markers to generate pitch, intensity, and durational patterns for the synthesis module of the system. In this paper, a novel method for annotating the prosodic structure of Thai sentences based on dependency representation of syntax is presented. The goal of the annotation process is to predict from text the rhythm of the input sentence when spoken according to its intended meaning. The encoding of the prosodic structure is established by minimizing speech disrhythmy while maintaining the congruency with syntax. That is, each word in the sentence is assigned a prosodic feature called strength dynamic which is based on the dependency representation of syntax. The strength dynamics assigned are then used to obtain rhythmic groupings in terms of a phonological unit called foot. Finally, the foot structure is used to predict the durational pattern of the input sentence. The aforementioned process has been tested on a set of ambiguous sentences, which represents various structural ambiguities involving five types of compounds in Thai.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.9
• /
• pp.39-47
• /
• 2012

The opinion of user on a certain product is expressed in positive/negative sentiments for specific features of it. In some cases, they are expressed for a holistic part of homogeneous specific features, or expressed for product itself. Therefore, in the area of opinion mining, name of opinion features to be extracted are specific feature names, holonyms for theses specific features, and product names. However, when the opinion target is described with product name or holonym, sometimes it may not match feature name of opinion sentence to true opinion target intended by the reviewer. In this paper, we present a method to extract opinion targets from opinion sentences. Most importantly, we propose a method to extract true target from the feature names mismatched to a intended target. First, we extract candidate opinion pairs using dependency relation between words, and then select feature names frequently mismatched to opinion target. Each selected opinion feature name is replaced to a specific feature intended by the reviewer. Finally, in order to extract relevant opinion features from the whole candidate opinion pairs including modified opinion feature names, candidate opinion pairs are rearranged by the order of user's interest.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2001.06a
• /
• pp.285-288
• /
• 2001

In this paper, we proposed new method of speech feature extraction using ICA(Independent Component Analysis) which minimized the dependency and correlation among speech signals on purpose to separate each component in the speech signal. ICA removes the repeating of data after finding the axis direction which has the greatest variance in input dimension. We verified improvement of speech recognition ability with training and recognition experiments when ICA compared with conventional mel-cepstrum features using HMM. Also, we can see that ICA dealt with the situation of recognition ability decline that is caused by environmental noise.

• Phonetics and Speech Sciences
• /
• v.2 no.4
• /
• pp.109-118
• /
• 2010

Using a speeded classification task (Garner, 1978), we investigated the perceptual interaction of distinctive features in Korean consonants. The main questions of this study were whether listeners can perceptually identify the component features that make up complex consonant sounds, whether these features are processed independently or dependently and whether there is a systematic hierarchy in their dependency. Participants were asked to classify syllables based on their difference in distinctive features in the task. Reaction times for this task were also gathered. For example, participants classified spoken syllables /ta/ and /pa/ as one category and /$t^ha$/ and /$p^ha$/ as another in terms of aspiration condition. In terms of articulation, participants classified /ta/ and /$t^ha$/ as one category and /pa/ and /$p^ha$/ as another. We assumed that the difference between their RTs represents their interdependency. We compared the laryngeal features and place features (Experiment 1), resonance features and place features (Experiment 2), and manner features and laryngeal features (Experiment 3). The results showed that distinctive features were not perceived in a completely independent way, but they had an asymmetric and hierarchical interdependency. The laryngeal features were found to be more independent compared to place and manner features. We discuss these results in the context of perceptual basis in phonology.

• Annual Conference on Human and Language Technology
• /
• 2006.10e
• /
• pp.148-155
• /
• 2006

한국어 구문 분석에서 가장 어려운 작업들 중에 하나는 종속절의 의존관계 파악이다. 본 논문에서는 이를 해결하기 위해서 종속절의 의존관계를 걸을 구성하는 서술어부(동사와 어미)의 관련 정보의 유무에 따라 의존관계가 성립한다고 가정했다. 즉 각각의 절들의 서술부의 관련 정보의 유무로 보고, 이진 분류 문제로 이 문제를 해결하였다. 사용한 자질은 정적 자질(static feature)와 동적 자질(dynamic feature)를 구성되어 있다. 정적 자질은 동사와 어미에서 표면적인 어휘 정보이고 이는 단어, POS 테그 및 위치 정보들이다. 동적 자질은 문장에서 절이 가지는 문법적인 형태를 의미하고, 이를 추출하기 위해 간단한 규칙을 만들고 이를 바탕으로 CKY 차트 파서를 통하여 추출하였다. 기계학습 방법으로는 이진 분류 문제에서 널리 사용되는 SVM을 사용하였다. 실험 결과 어휘 정보들 중에서 어미의 정보만 사용하였을 경우는 64.4%의 정확도를 보였고 문법적인 정보인 동적 자질을 사용한 경우는 73.5%로 어휘 정보만을 사용한 경우 보다 9.1%의 성능 향상됨을 보였다

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.727-729
• /
• 2005

나이브베이즈분류기($na\ddot{i}ve$ Bayes classifier)는 학습, 적용 및 계산자원 이용의 측면에서 매우 효율적인 모델이다. 또한, 그 분류 성능 역시 다른 기법에 비해 크게 떨어지지 않음이 다양한 실험을 통해 보여져 왔다. 특히, 데이터를 생성한 실제 확률분포를 나이브베이즈분류기가 정확하게 표현할 수 있는 경우에는 최대의 효과를 볼 수 있다. 하지만, 실제 확률분포에 존재하는 조건부독립성(conditional independence)이 나이브베이즈분류기의 구조와 일치하지 않는 경우에는 성능이 하락할 수 있다. 보다 구체적으로, 각 자질변수(feature variable)들 사이에 확률적 의존관계(probabilistic dependency)가 존재하는 경우 성능 하락은 심화된다. 본 논문에서는 이러한 나이브베이즈분류기의 약점을 효율적으로 해결할 수 있는 자질변수의 통합기법을 제시한다. 자질변수의 통합은 각 변수들 사이의 관계를 명시적으로 표현해 주는 방법이며, 특히 상호정보량(mutual information)에 기반한 통합 변수의 선정이 성능 향상에 크게 기여함을 실험을 통해 보인다.