• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2005년도 추계종합학술대회
• /
• pp.659-662
• /
• 2005

A parameterized FFT/IFFT core generator (PFFT_CoreGen) is designed, which can be used as an essential IP (Intellectual Property) in various OFDM modem designs. The PFFT_CoreGen generates Verilog-HDL models of FFT cores in the range of 64 ${\sim}$ 2048-point. To optimize the performance of the generated FFT cores, the PFFT_CoreGen can select the word-length of input data, internal data and twiddle factors in the range of 8-b ${\sim}$ 24-b. Some design techniques for low-power design are considered from algorithm level to circuit level.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 하계종합학술대회 논문집(3)
• /
• pp.19-22
• /
• 2000

This paper presents new on-line handwritten algorithm for continuous alphabet uppercase characters. The algorithm is based on the idea that alphabet uppercase character consists of at most 4 strokes. It tries to determine the maximum output for a recognition result among outputs of four recognizers which have the capacity to discriminate the character using from 1 through 4 stroke information. The recognition module has 4 neural network based recognizers, which can recognize from 1 through 4 stroke character. We also use specialized post-processing techniques for improving the recognition performance. Trained on 440 input data and choosing 390 uppercase words for a recognition test we reached a 92% recognition rate.

• 전자공학회논문지B
• /
• 제33B권5호
• /
• pp.127-137
• /
• 1996

In this paper, an algorithm for on-line rightward japanese parsing is proposed. The ambiguity in on-line parsing is accumulated until the input is completely finished, since there is not a space between words in the japanese sentence. Thus the algorithm for morphological analysis, based on modified chart, is used in solving it. And the number of searching a word in dirctionary for morphological analysis is also a puzzling problem. The japanese sentence, consist of N characters, has logically its maximum number of N(N+1)/2 searches in the ordinary on-line analysis, which is nearly twice as many as normal off-line. In this paper, the matter is settled through the modification of dictionary format. In experiment, we can accomplish the rate of analysis which is nearly equal to that of off-line parsing. And it becomes clear that the longer a sentence is, the better an analysis efficiency is.

• 한국산업정보학회논문지
• /
• 제4권3호
• /
• pp.52-58
• /
• 1999

본 논문에서는 한\ulcorner영 혼용문서인식을 위해 다중 크기, 다중 활자체에 적용 가능한 한글과 영어를 구별하는 알고리즘을 제안한다. 제안된 방법에서는 글자의 종횡비, 연결요소의 수, 좌상단의 획이미지 존재 여부, 그리고 바(bar)를 입력 이미지에 대해 좌상우하의 순서로 진행해 가면서 바를 검출하고, 이들을 이용하여 한글과 영어를 구별한다. 제안된 방법을 문서 작성 시 널리 사용되는 ？글의 명조체, 신명조체, 고딕체, 궁서체에 대해 실험하여 그 성능의 우수성을 입증하였다.

• 대한음성학회지:말소리
• /
• 제66호
• /
• pp.41-59
• /
• 2008

Knowledge in linguistic rhythm of the target language plays a major role in foreign language proficiency. This study attempts to discover valid rhythm features that can be utilized in automatic assessment of non-native English pronunciation. Eight previously proposed and two novel rhythm metrics are investigated with 360 English read speech tokens obtained from 27 Korean learners and 9 native speakers. It is found that some of the speech-rate normalized interval measures and above-word level metrics are effective enough to be further applied for automatic scoring as they are significantly correlated with speakers' proficiency levels. It is also shown that metrics need to be dynamically selected depending upon the structure of target sentences. Results from a preliminary auto-scoring experiment through a Multi Regression analysis suggest that appropriate control of unexpected input utterances is also desirable for better performance.

• 정보처리학회논문지B
• /
• 제11B권7호
• /
• pp.861-866
• /
• 2004

자판은 문자론 대상으로 인간과 인지단말기 사이를 이어주는 연결고리로서 인지활동으로 얻어진 지적 내용물을 정보기구로 입력시키는 장치다. 이러한 이유로 자판은 인간과 기계가 어울려지는 인기일체(人機一體)시스템으로 "인지 공학적 고려"와 "행동 과학적 효율"이 동시에 고려해야한다. 본 논문은 정음한글의 정보공학적 특성을 반영하여 한손자판을 배치 하였고, 어문결합에 의한 오인식 정정 및 문장 편집이 가능한 정음한손자판을 설계 및 구현 하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1987년도 전기.전자공학 학술대회 논문집(II)
• /
• pp.1166-1169
• /
• 1987

A new analog-la-digital structure. called cyclic-parallel analog-to-digital(A/D) converter, has been developed for video applications. It consists of a M-bit parallel A/D converter, a digital-to-analog(D/A) converter, a differencing amplifier with gain of $2^M$ and two sample-and-hold circuits. In this structure, the input signal is circulated around the circuits K times, thereby converted into a MK-bit digital word. The proposed converter retains speed advantages of conventional series-parallel converters, with half reduced circuit components.

• The Journal of the Acoustical Society of Korea
• /
• 제15권4E호
• /
• pp.21-27
• /
• 1996

In this paper, we propose a discriminative training algorithm for the stochastic segment model (SSM) in continuous speech recognition. As the SSM is usually trained by maximum likelihood estimation (MLE), a discriminative training algorithm is required to improve the recognition performance. Since the SSM does not assume the conditional independence of observation sequence as is done in hidden Markov models (HMMs), the search space for decoding an unknown input utterance is increased considerably. To reduce the computational complexity and starch space amount in an iterative training algorithm for discriminative SSMs, a hybrid architecture of SSMs and HMMs is programming using HMMs. Given the segment boundaries, the parameters of the SSM are discriminatively trained by the minimum error classification criterion based on a generalized probabilistic descent (GPD) method. With the discriminative training of the SSM, the word error rate is reduced by 17% compared with the MLE-trained SSM in speaker-independent continuous speech recognition.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.77.4-77
• /
• 2002

Communicating devices for the seriously disabled using eye-ball movement or some body movement are proposed. The first one is a device to use image processing, whose input signal is eyeball movement, A feature of this device is that the device can be readily realized using a note-book computer with USB (Universal Serial Bus) interface bus. This device is incorporated with a word processing software called Nearly Ladder. The second one is an emergency call switch which is used by a patient who can move his finger slightly. The patients can switch on the emergency switch only by touching a switch with his finger. The essence of this sensor is a touch sensor. The sensor can be realized using onl...

• 전자공학회논문지A
• /
• 제31A권4호
• /
• pp.127-135
• /
• 1994

In this paper we propose an EWLD(Enhanced Weighted Levenshtein Distance) algorithm to organize code-string pattern matching linear array processor based on the mappting to an one-dimensional array from a two-dimensional matching matrix, and design a processing element(PE) of the processor, N PEs are required instead of NS02T in the processor because of the mapping. Data input and output between PEs and all internal operations of each PE are performed in bit-serial fashion. The bit-serial operation consists of the computing of word distance (WD) by comparison and the selection of optimal code transformation path, and takes 22 clocks as a cycle. The layout of a PE is designed based on the double metal $1.5\mu$m CMOS rule. About 1,800 transistors consistute a processing element and 2 PEs are integrated on a 3mm$\times$3mm sized chip.