• Journal of Broadcast Engineering
• /
• v.21 no.6
• /
• pp.977-985
• /
• 2016

In this paper, we propose a new method for on-line genre classification using spectrogram and deep neural network. For on-line processing, the proposed method inputs an audio signal for a time period of 1sec and classifies its genre among 3 genres of speech, music, and effect. In order to provide the generality of processing, it uses the spectrogram as a feature vector, instead of MFCC which has been widely used for audio analysis. We measure the performance of genre classification using real TV audio signals, and confirm that the proposed method has better performance than the conventional method for all genres. In particular, it decreases the rate of classification error between music and effect, which often occurs in the conventional method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.7
• /
• pp.842-848
• /
• 2020

Music markets have entered the era of streaming. In order to select and propose music that suits the taste of music consumers, there is an active demand and research on an automatic music genre classification system. We propose a method to improve the accuracy of genre unclassified songs, which was a lack of the previous system, by using a generative adversarial network (GAN) to further develop the automatic voting system for deep learning music genre using Softmax proposed in the previous paper. In the previous study, if the spectrogram of the song was ambiguous to grasp the genre of the song, it was forced to leave it as an unclassified song. In this paper, we proposed a system that increases the accuracy of genre classification of unclassified songs by converting the spectrogram of unclassified songs into an easy-to-read spectrogram using GAN. And the result of the experiment was able to derive an excellent result compared to the existing method.

• Journal of Digital Contents Society
• /
• v.18 no.6
• /
• pp.1119-1125
• /
• 2017

Genres and actions of stories can be used to classify stories, and used effectively as well for visualizing story properties. This paper proposes a Genre-Action coordinate system for visualizing story property data in 2-dimension that has similarities between the genre and action items along the axes, i.e. a property of spatial continuum. With the proposed Genre-Action coordinate system we found that the genre and action items in the axes are arranged according to their similarities and we were able to achieve a spatially meaningful visualization of story properties where the related data form clusters.

• Proceedings of the Korea Contents Association Conference
• /
• 2018.05a
• /
• pp.97-98
• /
• 2018

재즈 연주자들이 음반에 많이 녹음한 재즈 스탠더드 곡을 대상으로 레퍼토리의 장르를 분류하여 선정한 곡을 중심으로 다른 버전의 편곡 특성을 연구한다. 레퍼토리 곡은 재즈 스탠더드 원곡에서 블루스, 스윙, 발라드, 비밥, 라틴의 5가지 장르로 분류되며, 대부분 발라드와 스윙이다. 레퍼토리의 곡 분류를 통해 같은 곡이 다른 버전에서 어떻게 다르게 연주되었는지 보기위해 여성 재즈보컬들에 의해 녹음된 음반을 중심으로 각 버전의 특징을 분석한다. 이 연구를 수행하여 각 여성 재즈 보컬들의 녹음된 곡에서 다른 버전의 편곡 특성을 도출한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.9
• /
• pp.4212-4217
• /
• 2013

Since genre of popular music began to classified, Alternative Music has been music form with most complex and diverse sub genre. This paper focused on mostly Alternative Rock, which began to attract attention since the 1990's, and analysed the cause for ambiguity of this genre. Therefore we can examine the inevitable limitation of traditional - based on musical form only - classification.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.06a
• /
• pp.90-91
• /
• 2016

본 논문에서는 스펙트로그램을 이용한 딥 러닝 기반의 오디오 장르 분류 기술을 제안한다. 기존의 오디오 장르 분류는 대부분 GMM 알고리즘을 이용하고, GMM의 특성에 따라 입력 성분들이 서로 직교한 성질을 갖는 MFCC를 오디오의 특성으로 사용한다. 그러나 딥 러닝을 입력의 성질에 제한이 없으므로 MFCC보다 가공되지 않은 특성을 사용할 수 있고, 이는 오디오의 특성을 더 명확히 표현하기 때문에 효과적인 학습을 할 수 있다. 본 논문에서는 딥 러닝에 효과적인 특성을 구하기 위하여 스펙트로그램(spectrogram)을 사용하여 오디오 특성을 추출하는 방법을 제안한다. 제안한 방법을 사용한면 MFCC를 특성으로 하는 딥 러닝보다 더 높은 인식률을 얻을 수 있다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2017.06a
• /
• pp.29-30
• /
• 2017

본 논문에서는 인간의 청각 기관을 모델링 한 스파이크그램 (spikegram)을 이용한 심층 신경망 기반의 음악 장르 분류 기술을 제안한다. 분류 대상은 GTZAN 데이터 세트의 10개 장르로 정의한다. 본 논문에서는 청각 기관의 인식 방법을 모델링한 방법을 이용하여 스파이크그램을 구하고, 스파이크그램에서 새로운 특성 벡터를 추출하는 방법을 제안한다. 제안하는 방법을 통해 심층 신경망에 적합한 특성 벡터를 구하고 이렇게 구한 특성 벡터로 신경망을 학습시켜 기존에 사용하던 다양한 방법들보다 높은 성능을 얻을 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.04a
• /
• pp.925-927
• /
• 2014

최근 멀티미디어 데이터의 핵심이 되는 음악 데이터가 매우 중요한 관심이 되고 있다. 멀티미디어 데이터 가운데서도 음악 데이터의 중요성이 높아지고 있는데 방대한 음악 데이터를 분류하는 것은 중요하다. 본 논문에서는 음악 데이터를 효과적으로 분류하기 위하여 화음의 다양한 정보를 저장하는 데이터 구조를 제안하고 각 장르별 고유한 화음 진행의 특징을 제시한다. 또한, 그 중 화음을 저장하는 데이터만을 추출하여 장르별 화음진행 특성에 기반 하여 3가지 음악 장르를 분류 할 것이다.

• The Journal of the Acoustical Society of Korea
• /
• v.27 no.3
• /
• pp.111-118
• /
• 2008

In this paper, we propose a new automatic taxonomy generation algorithm for the audio genre classification. The proposed algorithm automatically generates hierarchical taxonomy based on the estimated classification accuracy at all possible nodes. The estimation of classification accuracy in the proposed algorithm is conducted by applying the training data to classifier using k-fold cross validation. Subsequent classification accuracy is then to be tested at every node which consists of two clusters by applying one-versus-one support vector machine. In order to assess the performance of the proposed algorithm, we extracted various features which represent characteristics such as timbre, rhythm, pitch and so on. Then, we investigated classification performance using the proposed algorithm and previous flat classifiers. The classification accuracy reaches to 89 percent with proposed scheme, which is 5 to 25 percent higher than the previous flat classification methods. Using low-dimensional feature vectors, in particular, it is 10 to 25 percent higher than previous algorithms for classification experiments.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.1
• /
• pp.62-69
• /
• 2015

This study examined the effects of the level of narrativity of a culture content on the level of preference of a related culture content. The culture contents were categorized into novels, cartoons and TV programs according to the content type, and into dramas, comedies, and actions by the contents genre because previous studies found a high level of narrativity in novels and dramas. Based on the survey data on the movie preference, the following were found. First, when people prefer novels with high-level narrativity, rather than TV programs, which have low-level narrativity in a certain genre, they prefer watching movies in the same genre. Second, this relationship is even more reinforced when the genre of the original of the movie is drama, which has high-level narrativity, rather than comedies or actions, which have low-level narrativity. Narrativity plays an important role in the movie preference, especially when it comes to movie originals.