• 한국통신학회논문지
• /
• 제42권4호
• /
• pp.892-898
• /
• 2017

본 논문은 차량 내 AVN(Audio Video Navigation)에서 차량정보 분석과 제스처 인식이 가능한 소프트웨어 구조를 설계하고 구현 방법을 서술한다. 설계된 소프트웨어는 차량정보 분석을 위해 CAN(Controller Area Network) 통신 데이터 분석 모듈을 구현하여 차량의 주행 상태를 분석했다. AVN 소프트웨어는 분석된 정보를 웨어러블 디바이스의 제스처 정보와 융합토록 했다. 도출된 융합정보는 운전자의 명령 수행 단계로 매칭하고 서비스를 지원하는데 사용됐다. 설계된 AVN 소프트웨어는 기성 제품과 유사한 환경의 HW 플랫폼 상에 구현되어 차량 주행 상황과 동일하게 모사된 상황에서의 차량정보분석, 제스처 인식 수행 등의 기능을 지원함을 확인했다.

• ETRI Journal
• /
• 제19권4호
• /
• pp.344-362
• /
• 1997

The delay which is one of the quality of service parameters is considered to be a crucial factor for the effective usage of real-time audio and video streams in interactive multimedia collaborations. Among the various causes of the delay, we focus in this paper on the local delay concerned with the schemes which handle continuous inflow of encoded data from constant or variable bit-rate audio and video encoders. We introduce two kinds of implementation approaches, pull model and push model. While the pull model periodically pumps out the incoming data from the system buffer, the push model receives events from the device drivers. From our experiments based on Windows NT 3.51, it is shown that the push model outperforms the other for both constant and variable bit-rate streams in terms of the local delay, when the system suffers reasonable loads. We interpret this experimental data with M/G/1 multiple vacation queuing theories, and show that it is consistent with the queuing theoretic interpretations.

• 전자공학회논문지T
• /
• 제35T권1호
• /
• pp.120-124
• /
• 1998

음성 신호의 특성과 LD-CELP 알고리즘의 코드북 인덱스 검색 현황을 조사한 결과, 전 단계에서 검색된 코드북 인덱스가 다음 단계에서도 쓰이게 되는 것을 알 수 있었다. LD-CELP 알고리즘은 음성의 분석 구간을 짧게하여 음성의 명료도가 좋은 편이나, 최적의 코드를 검색하기 위해 많은 계산량이 발생하는 단점이 있다. 본 논문에서는 LD-CELP에서 검색된 코드북 인덱스를 저장하는 검색 메모리를 두어, 코드북의 검색 과정을 일부 생략하는 방법을 제안한다. 이 방법으로 샘플 음성을 시뮬레이션한 결과, 코드북 검색 계산량을 줄여 기존의 LD-CELP 방식보다 코드북 검색 시간을 3.2%-11.7%까지 줄일 수 있었다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2014년도 춘계학술발표대회
• /
• pp.992-994
• /
• 2014

Hemispheric asymmetry in prefrontal activation have been proposed in two decades ago, as measured by electroencephalographic (EEG) power in the theta band (4-8Hz), is related to reactivity to affectively pleasure audio stimuli. In this study, we designed an emotional audio stimulus experiment in order to verify frontal EEG asymmetry by analyzing ERSP results. Thirty healthy college students volunteered the stimulus experiment with the standard IADS affective sounds. These affective sound clips are classified in three emotion states, happy, neutral and fear. ERSP image results revealed that there are the stronger responses of high arousal (fear and happy) in the left prefrontal lobe, while the stronger responses of low arousal (neutral) in the right pre-frontal lobe. However, the high pleasure emotions (happy) can elicit greater relative right EEG activity, while the low and middle pleasure emotions (fear and neutral) can elicit the greater relative left EEG activity. Additionally, the most response differences of theta band have been found out in the medial frontal lobe, which is proved as the frontal midline theta.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권5호
• /
• pp.1590-1609
• /
• 2021

Laughter is one of the most important nonverbal sound that human generates. It is a means for expressing his emotions. The acoustic and contextual features of this specific sound are different from those of speech and many difficulties arise during their modeling process. During this work, we propose an audio laughter generation system based on unsupervised generative models: the autoencoder (AE) and its variants. This procedure is the association of three main sub-process, (1) the analysis which consist of extracting the log magnitude spectrogram from the laughter database, (2) the generative models training, (3) the synthesis stage which incorporate the involvement of an intermediate mechanism: the vocoder. To improve the synthesis quality, we suggest two hybrid models (LSTM-VAE, GRU-VAE and CNN-VAE) that combine the representation learning capacity of variational autoencoder (VAE) with the temporal modelling ability of a long short-term memory RNN (LSTM) and the CNN ability to learn invariant features. To figure out the performance of our proposed audio laughter generation process, objective evaluation (RMSE) and a perceptual audio quality test (listening test) were conducted. According to these evaluation metrics, we can show that the GRU-VAE outperforms the other VAE models.

• International Journal of Knowledge Content Development & Technology
• /
• 제14권3호
• /
• pp. 7-18
• /
• 2024

The present study focuses on the activities and efforts of the National Mission for Manuscripts (NMM) in the Uttar Pradesh region, which is known for its vast area, population, and rich cultural heritage. The aim is to examine the digitization work carried out by the NMM in this area, as digitization plays a crucial role in preserving our country's rich ancient heritage. The importance of safeguarding cultural heritage is universally acknowledged, and digitization serves as a vital tool in this endeavour. Through digitization, we can protect and preserve our heritage for future generations. The government has implemented several commendable initiatives for manuscript digitization, and the NMM stands as a prominent organization dedicated to the conservation of cultural heritage. The NMM possesses a diverse range of cultural heritage resources, including photographic slides, photographs, digital images, photo-negatives, motion pictures, audio spools, microfiche, LP records, endangered manuscripts, audio and videotapes, digital images, microfilms, digital audio and video files, and more. The mission has undertaken extensive digitization efforts to conserve and provide access to a significant portion of its collection. This study is unique as it explores the digital conservation and digitization practices of a premier institute working in the field of art and cultural heritage in Uttar Pradesh. With its extensive network of institutions, the mission aims to cover all manuscripts, digitize them, and consolidate them on a common platform for easy access and utilization.

• 한국음향학회지
• /
• 제27권5호
• /
• pp.229-238
• /
• 2008

음향 튜닝 과정을 통하여 카오디오의 음질은 개선되며 완성차의 품질 또한 향상된다. 하지만 소비자를 대상으로 한 선호도 조사 없이 소비자가 만족하도록 카오디오를 튜닝하는 것은 쉽지 않은 일이다. 소비자의 기호를 조사하기 위하여 주파수 특성, 밸런스, 공간감 등과 같은 매우 다양한 음향특성을 조사해야 하지만, 조사할 음향특성 항목이 많아질수록 비교 청취해야 하는 음원의 수가 급격히 증가하므로 여러 가지 문제점이 발행한다. 평가자의 피로도 증가로 인하여 실험이 어려워질 뿐 아니라, 개개의 음향특성과 전체의 음질의 연관성을 파악하는 것 또한 쉽지 않다. 본 연구에서는 음질 선호도를 조사할 때에 비교 청취되는 음원의 수를 크게 줄일 수 있도록 통계적 직교배열법을 사용하였으며, 분산분석법을 이용하여 청취실험 자료를 분석하였다. 특히, 직교배열법을 사용하여 여덟 가지 음향특성들의 256 가지 조합으로 이루어진 음향 환경을 16가지 비교음원을 사용하여 재생하였다. 분산분석 결과, 팝 음원의 경우에는 Treble이 일반적으로 재생된 음향의 음질 선호도에 가장 유의한 영향을 미치는 음향특성임을 밝혔다. 그 밖에도 Deep Bass와 SAD 및 Treble과 SAD의 교호작용 등이 유의한 음향특성으로 나타났다. 클래식 음원의 경우에는 SAD가 유일하게 유의하게 나타났다.

• 한국가정과교육학회지
• /
• 제9권1호
• /
• pp.1-17
• /
• 1997

This study was conducted to obtain basic materials to improve the teaching method of Home Economics by theoretically looking into the supplementary teaching materials or implements usable in teaching Costume History area. And based on these data, the types and the applications of the supplementary teaching materials or implements highschool owned were examined. The subjects of this study were 111 Home Economics and Housework curriculum highschool teachers who give a lecture in the country by using self-administered questionnaires. SAS program was used to calculate frequency, percentage, average, standard deviation, and $\chi$(sup)2-test analysis. The results of the study were as follows； 1. Most of the highschool teachers used the school expenses for experiments in preparing the supplementary teaching materials or implements. 2. Of the supplementary teaching materials and implements concerning Costume History, visual implements such as slides and pictures were the mostly owned. CD and audio implements as cassette-tapes were not used. 3. Most of the teachers recognized the importance of the audio-visual teaching materials and implements concerning Costume History. 4. Among the audio-visual materials and implements concerning Costume History by which can be made by school teachers of Home Economics and Housework curriculum, the mostly used one was ‘cutting pictorials from magazines and newspapers’, and the next were ‘orbital materials’, and ‘copy the pictorials’, and the least was ‘recording from the radio’. 5. Most of the annual expenses assigned to the department of Home Economics was used in cooking practice, and the least of the expenses was assigned in buying audio-visual teaching materials and implements. 6. Time assigned to the area of Home Economics was for the most part one or two hours per week, and among this, time assigned to the history of western costume and the history ok korean costume was for the most part five to eight hours. 7. The areas that the highschool teachers felt difficulties mostly during clothing and textiles curriculum were ‘textiles’and the next were ‘knitting’, ‘western costume history’, and ‘korean clothing construction’. 8. The difficulties the highschool teachers faced while teaching Costume History were mostly that ‘the pictorials in the text is not fully explainable’, the next were ‘most of the supplementary teaching materials or implements are not owned’, ‘have to explain very much in a short time’, and ‘the lectural explanation is insufficient’. 9. The solution for the difficulties that the highschool teachers faced while teaching Costume History was mostly ‘the information, on which audio-visual materials and implements are distributed in the market, should be easy to obtain’, the next opinions were ‘the school should provide enough experiment and practice expenses to buy audio-visual materials and implements’, and ‘education facilities of the Home Economics Department should be the main aspects in improving the teaching methods and should give special lectures about it’.

• 한국음향학회지
• /
• 제21권2호
• /
• pp.182-189
• /
• 2002

본 논문은 오디오 색인·검색 시스템을 구현하기 위하여 오디오 신호에 대한특징 파라메터 풀 (pool)을 구성하고 이에 따른 오디오 데이터의 내용분석 및 분류에 관한 연구이다. 오디오 데이터는 기본적인 다양한 오디오 형태로 분류되어진다. 본 논문에서는 오디오 데이터의 분류에 이용 가능한 특징 파라메터를 분석하고 추출방법에 대하여 논한다. 그리고 특징 파라메터 풀을 색인 그룹 단위로 구성하여 오디오 카테고리에 대한 설정된 특징들의 포함 정도와 색인기준을 오디오 데이터의 내용을 중심으로 비교 ·분석한다. 그리고 위의 결과를 바탕으로 분류절차를 구성하여 오디오 신호를 분류하는 모의실험을 행하였다.

• 대한음성학회지:말소리
• /
• 제61호
• /
• pp.63-74
• /
• 2007

Discrimination of music and speech from the multimedia signal is an important task in audio coding and broadcast monitoring systems. This paper deals with the problem of feature parameter extraction for discrimination of music and speech. The wavelet transform is a multi-resolution analysis method that is useful for analysis of temporal and spectral properties of non-stationary signals such as speech and audio signals. We propose new feature parameters extracted from the wavelet transformed signal for discrimination of music and speech. First, wavelet coefficients are obtained on the frame-by-frame basis. The analysis frame size is set to 20 ms. A parameter $E_{sum}$ is then defined by adding the difference of magnitude between adjacent wavelet coefficients in each scale. The maximum and minimum values of $E_{sum}$ for period of 2 seconds, which corresponds to the discrimination duration, are used as feature parameters for discrimination of music and speech. To evaluate the performance of the proposed feature parameters for music and speech discrimination, the accuracy of music and speech discrimination is measured for various types of music and speech signals. In the experiment every 2-second data is discriminated as music or speech, and about 93% of music and speech segments have been successfully detected.