• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2006.06a
• /
• pp.17-20
• /
• 2006

본 논문에서는 잡음이 첨가된 연속음성에서의 자동 음절분할을 위해 기존에 사용되고 있는 특징 파라미터인 단구간 에너지 이외에 잡음에 강인한 특성을 가지고 있는 새로운 특징인 스펙트럼 밀도비교척도와 의사역행렬을 이용한 선형판별함수를 제안한다. 기존에 사용되는 단구간 에너지는 잡음이 없는 환경에서는 좋은 성능을 나타내지만 잡음환경에서는 그렇지 못하다. 반면에 논문에서 제안한 척도들은 반대의 성능을 가지므로 주변잡음의 크기에 따라 각각의 파라미터를 적절한 가중치로 조합하는 음절구간 결정함수와 유한상태 머신을 추가로 사용면 무 잡음 환경뿐만 아니라, 잡음이 첨가된 연속음성에서도 일정수준 이상의 음절구간을 분리해 낼 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.355-357
• /
• 2020

언어 학습 음원 분석 방법 및 언어 학습 음원을 재생하는 전자 디바이스 연구로, 음원을 문장 단위로 분할하여 스크립트화하는 것을 주요 목표로 한다. 분석과정은 크게 세단계로 나눌 수 있다. 무음 구간 분석, 음원 분할 및 STT 구간, 스크립트 재구성이다. 이런 분석 과정을 통해 나온 결과물의 정확도는 90%로서 본 연구의 목표를 달성한다.

• The Journal of the Acoustical Society of Korea
• /
• v.32 no.2
• /
• pp.138-146
• /
• 2013

Passive sonars employ DEMON (Detection of Envelope Modulation on Noise) processing to extract propeller information from the radiated noise of underwater targets. Conventional DEMON processing improves SNR(Signal to Noise Ratio) characteristic by Welch method. The conventional Welch method overlaps several different time domain DEMON outputs to reduce the variance. However, the conventional methods have high computational complexity to get high SNR with correlated acoustic signals. In this paper, we propose new DEMON processing method that divides acoustic signal into several frequency bands before DEMON processing and averages each DEMON outputs. Therefore, the proposed method gathers independent acoustic signal faster than conventional method with low computational complexity. We prove the performance of the proposed method with mathematical analysis and computer simulations.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.8
• /
• pp.24-30
• /
• 2001

This article is concerned with automatic segmentation for Korean speech signals. All kinds of transition cases of phonetic units are classified into 3 types and different strategies for each type are applied. The type 1 is the discrimination of silence, voiced-speech and unvoiced-speech. The histogram analysis of each indicators which consists of wavelet coefficients and SVF (Spectral Variation Function) in wavelet coefficients are used for type 1 segmentation. The type 2 is the discrimination of adjacent vowels. The vowel transition cases can be characterized by spectrogram. Given phonetic transcription and transition pattern spectrogram, the speech signal, having consecutive vowels, are automatically segmented by the template matching. The type 3 is the discrimination of vowel and voiced-consonants. The smoothed short-time RMS energy of Wavelet low pass component and SVF in cepstral coefficients are adopted for type 3 segmentation. The experiment is performed for 342 words utterance set. The speech data are gathered from 6 speakers. The result shows the validity of the method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.626-628
• /
• 2016

본 논문에서는 이진 영상에서 일부 정보가 손실된 경우에 히스토그램을 분석하여 구간을 분할한 후, 오츠 이진화와 퍼지 이진화 기법을 적용하여 원 영상을 이진화 한 후에 홉필드 네트워크를 적용하여 영상을 복원하는 방법을 제안한다. 제안된 방법은 그레이 영상에서 히스토그램을 분석하여 픽셀 값의 변화의 폭이 큰 부분들을 분석하여 구간들을 분할하고 변화의 폭이 큰 부분의 지점에 속하는 영역은 오츠 이진화 기법을 적용하여 이진화하고 그 외의 구간들은 퍼지 이진화 기법을 적용하여 영상을 이진화 한다. 그리고 이진화 된 영상을 홉필드 네트워크를 적용하여 학습한다. 실험 영상에 정보 손실이 발생한 영상을 대상으로 제안된 방법을 적용한 결과, 대부분의 정보 손실이 있는 영상에서 모두 복원되는 것을 확인하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.8A
• /
• pp.1206-1212
• /
• 2000

The subscriber loop subnet at domestic wired telephony networks uses one circuit per one subscriber and the transmission network subnet uses TDM that is composed to 30 voice channels and is assigned to 64kbps per one voice channel of 2.048Mbps in El. On the contrary, the subscriber networks for cellular networks is extent to channel capacity and make it efficiency use CDMA method but the transmission network is used to the same as telephony. In this paper, The subscriber loop at wired network also is shown to increasing effective and lower expensive using CDM.

• The KIPS Transactions:PartD
• /
• v.11D no.5
• /
• pp.1011-1020
• /
• 2004

A lot of work has been done to improve the I/O performance of such a system that store and manage a massive amount of data by distributing them across multiple disks and access them in parallel. Most of the previous work has focused on an efficient mapping from a grid ceil, which is determined bY the interval number of each dimension, to a disk number on the assumption that each dimension is split into disjoint intervals such that entire data space is GRID-like partitioned. However, they have ignored the effects of a GRID partitioning scheme on declustering performance. In this paper, we enhance the performance of mapping function based declustering algorithms by applying a good GRID par-titioning method. For this, we propose an estimation model to count the number of grid cells intersected by a range query and apply a GRID partitioning scheme which minimizes query result size among the possible schemes. While it is common to do binary partition for high-dimensional data, we choose less number of dimensions than needed for binary partition and split several times along that dimensions so that we can reduce the number of grid cells touched by a query. Several experimental results show that the proposed estimation model gives accuracy within 0.5% error ratio regardless of query size and dimension. We can also improve the performance of declustering algorithm based on mapping function, called Kronecker Sequence, which has been known to be the best among the mapping functions for high-dimensional data, up to 23 times by applying an efficient GRID partitioning scheme.

• Proceedings of the KAIS Fall Conference
• /
• 2010.11a
• /
• pp.176-179
• /
• 2010

본 논문에서는 고속철도 폐색분할 설계를 위한 요구사항을 도출하였다. 경부고속철도 열차제어시스템은 고정폐색방식으로 KTX가 차량의 물리적 특성, 선로환경 등을 고려하여 분할된 폐색구간을 진입할 때, 선행열차의 점유폐색을 기준으로 궤도회로로부터 해당폐색의 열차 진입/진출속도, 운행가능거리, 감속도 등의 운행정보를 전송받는다. 그리고 차상열차제어시스템은 지상에서 수신한 운행정보를 통해 열차제어곡선을 생성하고 열차가 해당폐색의 기준속도를 초과했을 경우, 비상제동명령을 내려 열차의 안전한 운행을 보장한다. 폐색분할은 열차의 안전한 운행을 위해 고정폐색방식에서 수행되는 기본설계로, 폐색분할 설계 결과는 궤도회로를 비롯한 지상열차제어장치의 수량을 산정하는 기준이 된다. 따라서 본 논문에서는 최고운행속도 300km/h로 운행하는 경부고속철도 폐색분할 설계를 기준으로 폐색분할을 위한 입력요구사항에 대해 분석하였다.

• The Journal of the Acoustical Society of Korea
• /
• v.31 no.4
• /
• pp.266-272
• /
• 2012

Speaker segmentation is a process of automatically detecting the speaker boundary points in the audio data. Speaker segmentation methods are divided into two categories depending on whether they use a prior knowledge or not: One is the model-based segmentation and the other is the metric-based segmentation. In this paper, we introduce the eigenvoice-based speaker weight distance method and compare it with the representative metric-based methods. Also, we employ and compare the Euclidean and cosine similarity functions to calculate the distance between speaker weight vectors. And we verify that the speaker weight distance method is computationally very efficient compared with the method directly using the distance between the speaker adapted models constructed by the eigenvoice technique.

• The KIPS Transactions:PartD
• /
• v.16D no.4
• /
• pp.487-496
• /
• 2009

This paper addresses an indexing scheme capable of efficiently processing range queries in a large-scale trajectory database. After discussing the drawbacks of previous indexing schemes, we propose a new scheme that divides the temporal dimension into multiple time intervals and then, by this interval, builds an index for the line segments. Additionally, a supplementary index is built for the line segments within each time interval. This scheme can make a dramatic improvement in the performance of insert and search operations using a main memory index, particularly for the time interval consisting of the segments taken by those objects which are currently moving or have just completed their movements, as contrast to the previous schemes that store the index totally on the disk. Each time interval index is built as follows: First, the extent of the spatial dimension is divided onto multiple spatial cells to which the line segments are assigned evenly. We use a 2D-tree to maintain information on those cells. Then, for each cell, an additional 3D $R^*$-tree is created on the spatio-temporal space (x, y, t). Such a multi-level indexing strategy can cure the shortcomings of the legacy schemes. Performance results obtained from intensive experiments show that our scheme enhances the performance of retrieve operations by 3$\sim$10 times, with much less storage space.