• Journal of Platform Technology
• /
• v.11 no.3
• /
• pp.12-23
• /
• 2023

In the 2020s, the K-Pop market has been dominated by girl groups over boy groups and the fourth generation over the third generation. This paper presents methods and results on lyric clustering to investigate whether the generation of girl groups has started to change. We collected meta-information data for 1469 songs of 47 groups released from 2013 to 2022 and classified them into lyric information and non-lyric meta-information and quantified them respectively. The lyrics information was preprocessed by applying word-translation frequency vectorization based on previous studies and then selecting only the top vector values. Non-lyric meta-information was preprocessed and applied with One-Hot Encoding to reduce the bias of using only lyric information and show better clustering results. The clustering performance on the preprocessed data is 129%, 45% higher for Spherical K-Means' Silhouette Score and Calinski-Harabasz Score, respectively, compared to Hierarchical Clustering. This paper is expected to contribute to the study of Korean popular song development and girl group lyrics analysis and clustering.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.10a
• /
• pp.722-724
• /
• 2012

문서 군집화를 통하여 문서를 효율적으로 조직, 관리, 검색 할 수 있다. 일반적으로 문서 군집화는 많은 단어와 개념들을 포함하고 있기 때문에 차원이 큰 벡터 공간 모델에서 군집화를 수행한다. 본 논문에서 문서 집합에 대응하는 온톨로지를 이용하여 문서 벡터 공간의 차원을 줄여 효율적으로 군집화하는 방법을 제안하고, 실험을 통하여 기존 방법보다 우수함을 보인다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 1998.04a
• /
• pp.116-121
• /
• 1998

본 논문에서는 데이터의존성과 벡터왜곡척도를 이용하여 개선된 칼라영상을 복호화하였다. 프랙탈 칼라영상의 복원방법은 Zhang과 Po의 벡터왜곡척도를 이용한 R, G, B 칼라 성분간의 상관관계를 고려하여 부호화한 압축파일을 사용하여 수렴될 복원영상을 독립적인 반복변환에 의해 수렴되는 영역과 데이터의존성을 갖는 영역으로 분류하여 데이터의존성 부분이 차지하는 만큼 복호화 과정에서 불필요한 계산량이 제거되었고, R 영역에서 검색한 데이터 의존영역을 G, B 영역에 그대로 사용하여 고속복호화가 가능하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.97-99
• /
• 2004

본 논문에서는 다차원 데이터의 유사도 검색을 효과적으로 수행하기 위한 색인 구조를 제안한다. 제안하는 색인 구조는 차원의 저주 현상을 극복하기 위한 벡터 근사 기반의 색인 구조이다. 제안하는 색인 구조는 부모 노드를 기준으로 KDB-트리와 유사한 영역 분할 방식으로 분할하고 분할된 각 영역은 데이터의 분포 특성에 따라 동적 비트를 할당하여 벡터 근사화된 영역을 표현한다. 따라서, 하나의 노드 안에 않은 영역 정보를 저장하여 트리의 깊이를 줄일 수 있다. 또한 다차원의 특징 벡터 공간에 상대적인 비트를 할당하기 때문에 군집화되어 있는 데이터에 대해서 효과적이다 제안하는 색인 구조의 우수성을 보이기 위해 다양한 실험을 통하여 성능의 우수성을 입증한다.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.1
• /
• pp.149-160
• /
• 1997

This paper is concerned with the problem of speaker-adaptive speech synthes is method using a mapped codebook designed by fuzzy mapping on FLVQ (Fuzzy Learning Vector Quantization). The FLVQ is used to design both input and reference speaker's codebook. This algorithm is incorporated fuzzy membership function into the LVQ(learning vector quantization) networks. Unlike the LVQ algorithm, this algorithm minimizes the network output errors which are the differences of clas s membership target and actual membership values, and results to minimize the distances between training patterns and competing neurons. Speaker Adaptation in speech synthesis is performed as follow;input speaker's codebook is mapped a reference speaker's codebook in fuzzy concepts. The Fuzzy VQ mapping replaces a codevector preserving its fuzzy membership function. The codevector correspondence histogram is obtained by accumulating the vector correspondence along the DTW optimal path. We use the Fuzzy VQ mapping to design a mapped codebook. The mapped codebook is defined as a linear combination of reference speaker's vectors using each fuzzy histogram as a weighting function with membership values. In adaptive-speech synthesis stage, input speech is fuzzy vector-quantized by the mapped codcbook, and then FCM arithmetic is used to synthesize speech adapted to input speaker. The speaker adaption experiments are carried out using speech of males in their thirties as input speaker's speech, and a female in her twenties as reference speaker's speech. Speeches used in experiments are sentences /anyoung hasim nika/ and /good morning/. As a results of experiments, we obtained a synthesized speech adapted to input speaker.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.2
• /
• pp.60-69
• /
• 1998

This paper proposes a speech synthesis method using Fuzzy VQ, and then study how to make choice of fuzziness value which optimizes (controls) the performance of FVQ in order to obtain the synthesized speech which is closer to the original speech. When FVQ is used to synthesize a speech, analysis stage generates membership function values which represents the degree to which an input speech pattern matches each speech patterns in codebook, and synthesis stage reproduces a synthesized speech, using membership function values which is obtained in analysis stage, fuzziness value, and fuzzy-c-means operation. By comparsion of the performance of the FVQ and VQ synthesizer with simmulation, we show that, although the FVQ codebook size is half of a VQ codebook size, the performance of FVQ is almost equal to that of VQ. This results imply that, when Fuzzy VQ is used to obtain the same performance with that of VQ in speech synthesis, we can reduce by half of memory size at a codebook storage. And then we have found that, for the optimized FVQ with maximum SQNR in synthesized speech, the fuzziness value should be small when the variance of analysis frame is relatively large, while fuzziness value should be large, when it is small. As a results of comparsion of the speeches synthesized by VQ and FVQ in their spectrogram of frequency domain, we have found that spectrum bands(formant frequency and pitch frequency) of FVQ synthesized speech are closer to the original speech than those using VQ.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.4A
• /
• pp.394-402
• /
• 2008

In this paper, we propose a novel soft output generation method for spatially multiplexed MIMO systems. The receiver complexity of spatially mutiplexed MIMO system is in proportion to the number of candidate vectors. The ML signal detection method considers all possible vectors as candidates, thereby achieving a high performance, however, its complexity is very high. Low complexity receiver techniques involving a small number of candidate vectors, provide soft output values of low reliability. In this paper, we propose a method to improve reliability of the soft output values obtained using a small number of candidate vectors.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.2
• /
• pp.1-9
• /
• 2024

In this paper, we propose a new method to visualize different vector field patterns from density data. We use moving least squares (MLS), which is used in physics-based simulations and geometric processing. However, typical MLS does not take into account the nature of density, as it is interpolated to a higher order through vector-based constraints. In this paper, we design an algorithm that incorporates Monte Carlo-based weights into the MLS to efficiently account for the density characteristics implicit in the input data, allowing the algorithm to represent different forms of white noise. As a result, we experimentally demonstrate detailed vector fields that are difficult to represent using existing techniques such as naive MLS and divergence-constrained MLS.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.8
• /
• pp.583-589
• /
• 2004

Proposed is a speaker normalization method based on vector quantizer for continuous speech recognition (CSR) system in which no acoustic information is made use of. The proposed method, which is an improvement of the previously reported speaker normalization scheme for a simple digit recognizer, builds up a canonical codebook by iteratively training the codebook while the size of codebook is increased after each iteration from a relatively small initial size. Once the codebook established, the warp factors of speakers are estimated by comparing exhaustively the warped versions of each speaker's utterance with the codebook. Two sets of phones are used to estimate the warp factors: one, a set of vowels only. and the other, a set composed of all the Phonemes. A Piecewise linear warping function which corresponds to the estimated warp factor is adopted to warp the power spectrum of the utterance. Then the warped feature vectors are extracted to be used to train and to test the speech recognizer. The effectiveness of the proposed method is investigated by a set of recognition experiments using the TIMIT corpus and HTK speech recognition tool kit. The experimental results showed comparable recognition rate improvement with the formant based warping method.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 1996.06a
• /
• pp.703-706
• /
• 1996