• International Journal of Internet, Broadcasting and Communication
• /
• 제16권3호
• /
• pp.27-32
• /
• 2024

Reliable and fine-grained musical metadata are required for efficient search of rapidly increasing music files. In particular, since the primary motive for listening to music is its emotional effect, diversion, and the memories it awakens, emotion classification along with genre classification of music is crucial. In this paper, as an initial approach towards a "ground-truth" dataset for music emotion and genre classification, we elaborately generated a music corpus through labeling of a large number of ordinary people. In order to verify the suitability of the dataset through the classification results, we extracted features according to MPEG-7 audio standard and applied different machine learning models based on statistics and deep neural network to automatically classify the dataset. By using standard hyperparameter setting, we reached an accuracy of 93% for genre classification and 80% for emotion classification, and believe that our dataset can be used as a meaningful comparative dataset in this research field.

• International Journal of Computer Science & Network Security
• /
• 제23권9호
• /
• pp.47-54
• /
• 2023

For Bengali music emotion classification, deep learning models, particularly CNN and RNN are frequently used. But previous researches had the flaws of low accuracy and overfitting problem. In this research, attention-based Conv1D and BiGRU model is designed for music emotion classification and comparative experimentation shows that the proposed model is classifying emotions more accurate. We have proposed a Conv1D and Bi-GRU with the attention-based model for emotion classification of our Bengali music dataset. The model integrates attention-based. Wav preprocessing makes use of MFCCs. To reduce the dimensionality of the feature space, contextual features were extracted from two Conv1D layers. In order to solve the overfitting problems, dropouts are utilized. Two bidirectional GRUs networks are used to update previous and future emotion representation of the output from the Conv1D layers. Two BiGRU layers are conntected to an attention mechanism to give various MFCC feature vectors more attention. Moreover, the attention mechanism has increased the accuracy of the proposed classification model. The vector is finally classified into four emotion classes: Angry, Happy, Relax, Sad; using a dense, fully connected layer with softmax activation. The proposed Conv1D+BiGRU+Attention model is efficient at classifying emotions in the Bengali music dataset than baseline methods. For our Bengali music dataset, the performance of our proposed model is 95%.

• 한국컴퓨터그래픽스학회논문지
• /
• 제29권4호
• /
• pp.1-6
• /
• 2023

메타버스 환경에서의 배경음악은 사용자의 몰입감을 증진시키기 위해 사용된다. 하지만 현재 대부분의 메타버스 환경에서는 사전에 매칭시킨 음원을 반복 재생하며, 이는 빠르게 변화하는 사용자의 상호작용 맥락에 어울리지 못해 사용자의 몰입감을 저해시키는 경향이 있다. 본 논문에서는 보다 몰입감 있는 메타버스 대화 경험을 구현하기 위해 1) 한국어 멀티모달 감정 데이터셋인 KEMDy20을 이용하여 발화로부터 감정을 추출하는 회귀 신경망을 구현하고 2) 음원에 arousal-valence 레벨이 태깅되어 있는 DEAM 데이터셋을 이용하여 발화 감정에 대응되는 음원을 선택하여 재생한 후 3) 아바타를 이용한 실시간 대화가 가능한 가상공간과 결합하여 몰입형 메타버스 환경에서 발화의 감정에 어울리는 배경음악을 실시간으로 재생하는 시스템을 구현하였다.

• 스마트미디어저널
• /
• 제8권4호
• /
• pp.64-71
• /
• 2019

The performance of an OMR (Optical Music Recognition) system is usually determined by the characterizing features of the input music score images. Low resolution is one of the main factors leading to degraded image quality. In this paper, we handle the low-resolution problem using the super-resolution technique. We propose the use of a deep neural network with instance normalization to improve the quality of music score images. We apply instance normalization which has proven to be beneficial in single image enhancement. It works better than batch normalization, which shows the effectiveness of shifting the mean and variance of deep features at the instance level. The proposed method provides an end-to-end mapping technique between the high and low-resolution images respectively. New images are then created, in which the resolution is four times higher than the resolution of the original images. Our model has been evaluated with the dataset "DeepScores" and shows that it outperforms other existing methods.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2020년도 하계학술대회
• /
• pp.714-716
• /
• 2020

We propose a unique client-driven music genre classification solution, that can identify the music genre using a deep convolutional neural network operating on the time-domain signal. The proposed method uses the client device (Jetson TX2) computational resources to identify the music genre. We use the industry famous GTZAN genre collection dataset to get reliable benchmarking performance. HTTP live streaming (HLS) client and server sides are designed locally to validate the effectiveness of the proposed method. HTTP persistent broadcast connection is adapted to reduce corresponding responses and network bandwidth. The proposed model can identify the genre of music files with 97% accuracy. Due to simplicity and it can support a wide range of client hardware.

• International Journal of Contents
• /
• 제10권4호
• /
• pp.11-17
• /
• 2014

The influence of acquisition environment on music score images captured by a camera has not yet been seriously examined. All existing Optical Music Recognition (OMR) systems attempt to recognize music score images captured by a scanner under ideal conditions. Therefore, when such systems process images under the influence of distortion, different viewpoints or suboptimal illumination effects, the performance, in terms of recognition accuracy and processing time, is unacceptable for deployment in practice. In this paper, a novel, lightweight but effective approach for dealing with the issues caused by camera based music scores is proposed. Based on the staff line information, musical rules, run length code, and projection, all regions of interest are determined. Templates created from inverse filter are then used to recognize the music symbols. Therefore, all fragmentation and deformation problems, as well as missed recognition, can be overcome using the developed method. The system was evaluated on a dataset consisting of real images captured by a smartphone. The achieved recognition rate and processing time were relatively competitive with state of the art works. In addition, the system was designed to be lightweight compared with the other approaches, which mostly adopted machine learning algorithms, to allow further deployment on portable devices with limited computing resources.

• 한국음향학회지
• /
• 제36권6호
• /
• pp.436-441
• /
• 2017

음악 유사도 계산은 음악 검색 시스템 구현에 있어서 필수적인 구성 요소이다. 본 논문은 음악 검색 중에서 커버곡 검색에 대해서 다룬다. 크로마 n-gram을 이용한 커버곡 검색에 있어서 특징 DB 저장 공간을 줄이고 성능을 향상시키기 위해서 t-tab n-gram을 제안하고, n-gram 선택 방법, n-gram 집합 간 비교 방법에 관해서 연구하였다. 공개되어 있는 커버곡 데이터셋에서 실험을 수행하여 제안된 방법이 저장 공간을 줄이면서 동시에 커버곡 검색 성능을 향상시킬 수 있음을 보였다.

• 한국콘텐츠학회논문지
• /
• 제18권5호
• /
• pp.490-501
• /
• 2018

정보통신기술의 발달에 기반을 둔 디지털화의 급속한 기술 혁신은 디지털 콘텐츠 산업을 크게 변화시켰으며 스트리밍 서비스와 같은 새로운 형태의 서비스 출현으로 이어졌다. 그러나 스트리밍 서비스가 전통적인 다운로딩 서비스에 대한 위협인지 여부는 여전히 논란의 여지가 있으며, 어떻게 관련되어 있는지는 중요한 문제이다. 따라서, 본 연구에서는 음악 스트리밍 서비스가 음악 다운로드 서비스에 대해서 보완관계인지, 대체관계인지 여부를 분석하였다. 또한, LTE의 보급률이 이러한 대체 보완 관계에 어떻게 영향을 미쳤는지 살펴보았다. 한국의 온라인 음악 시장에서 선두적인 플랫폼 자료를 사용하여 분석한 결과, 음악 다운로드 서비스가 음악 스트리밍 서비스를 보완한다는 것을 보였고, 이러한 보완 관계는 LTE 기술 도입으로 강화되고 있다.

• 전기학회논문지
• /
• 제62권11호
• /
• pp.1598-1603
• /
• 2013

Recently, researches on analyzing relationship between the state of emotion and musical stimuli are increasing. In many previous works, data sets from all extracted channels are used for pattern classification. But these methods have problems in computational complexity and inaccuracy. This paper proposes a selection of optimal EEG channel to reflect the state of emotion efficiently according to music listening by analyzing stochastic feature vectors. This makes EEG pattern classification relatively simple by reducing the number of dataset to process.

• International Journal of Computer Science & Network Security
• /
• 제22권1호
• /
• pp.55-60
• /
• 2022

Churn prediction is a critical long-term problem for many business like music, games, magazines etc. The churn probability can be used to study many aspects of a business including proactive customer marketing, sales prediction, and churn-sensitive pricing models. It is quite challenging to design machine learning model to predict the customer churn accurately due to the large volume of the time-series data and the temporal issues of the data. In this paper, a parallel artificial neural network is proposed to create a highly-accurate customer churn model on a large customer dataset. The proposed model has achieved significant improvement in the accuracy of churn prediction. The scalability and effectiveness of the proposed algorithm is also studied.