• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2013.06a
• /
• pp.34-35
• /
• 2013

본 논문에서는 오디오 피크 검출을 적용한 TV 방송 프로그램내 배경음악 식별 알고리즘을 제안한다. 제안한 알고리즘은 음악 핑거프린트 추출 및 전송부, 음악구간 검출부, 음악 핑거프린트는 고속 매칭 및 정보전송부 세 부분으로 구성되어 있다. 음악 핑거프린트 추출 및 전송부에서는 음악 원음 오디오 데이터를 퓨리에 변환하여 스펙트럼 계수를 추출한다. 추출된 스펙트럼의 성분 중에서 일정한 문턱값 이상의 에너지를 가지는 값을 피크로 검출하고 검출된 피크를 이용하이 핑거프린트를 생성하고 데이터 베이스화한다. 음악구간 검출부에서는 입력된 방송 프로그램 오디오 데이터에 GMM(Gaussian Mixture Model)을 적용하여 음악과 음악 외 오디오 데이터를 분류한다. 음악 핑거프린트 고속 매칭 및 정보전송부에서는 음악구간이라고 인식된 쿼리 오디오 데이터를 음악 핑거프린트 추출 및 전송부와 동일한 과정을 통해 핑거프린트를 생성하고 데이터 베이스화된 음악 원음의 핑거프린트들과 비교하여 가장 유사한 음원의 정보를 TV의 화면에 자막으로 보여준다.

• The Journal of the Acoustical Society of Korea
• /
• v.32 no.5
• /
• pp.415-422
• /
• 2013

This paper proposes a robust binary audio fingerprinting method by minimizing hinge-loss function. In the proposed method, the type of fingerprints is binary, which is conducive in reducing the size of fingerprint DB. In general, the binarization of features for fingerprinting deteriorates the performance of fingerprinting system, such as robustness and discriminability. Thus it is necessary to minimize such performance loss. Since the similarity between two audio clips is represented by a hinge-like function, we propose a method to derive a binary fingerprinting by minimizing a hinge-loss function. The derived hinge-loss function is minimized by using the minimal loss hashing. Experiments over thousands of songs demonstrate that the identification performance of binary fingerprinting can be improved by minimizing the proposed hinge loss function.

• Journal of Broadcast Engineering
• /
• v.17 no.4
• /
• pp.659-669
• /
• 2012

This paper proposes the method to extract a binary audio fingerprint by combining several base binary fingerprints. Based on majority voting of base fingerprints, which are designed by mimicking the fingerprint used in Philips fingerprinting system, the proposed fingerprint is determined. In the matching part, the base fingerprints are extracted from the query, and distance is computed using the sum of them. In the experiments, the proposed fingerprint outperforms the base binary fingerprints. The method can be used for enhancing the existing binary fingerprint or for designing a new fingerprint.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.6
• /
• pp.716-723
• /
• 2019

Fingerprint matching accuracy is essential in deploying a music search service. This paper deals with a method to improve fingerprint matching accuracy by utilizing an auxiliary information which is called power weight. Power weight is an expected robustness of each hash bit. While the previous power mask binarizes the expected robustness into strong and weak bits, the proposed method utilizes a real-valued function of the expected robustness as weights for fingerprint matching. As a countermeasure to the increased storage cost, we propose a compression method for the power weight which has strong temporal correlation. Experiments on the publicly-available music datasets confirmed that the proposed power weight is effective in improving fingerprint matching performance.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.1182-1187
• /
• 2006

본 논문은 필립스의 오디오 핑거프린트 추출 방식을 기반으로 기존의 방식이 주파수 영역을 너무 조밀하게 분석하는 특징을 지적하고 개선 방안으로 양자화를 통해 필터 뱅크의 에너지 변화율을 오디오 핑거프린트 추출시 반영하는 방법을 제안하였다. 또한 제안된 알고리즘을 사용하여 PDA 로 실제 어플리케이션을 구현하는 것을 목적으로 하고 있다. 제안된 방식은 필립스 방식과 동일한 메모리 크기를 유지하기 위하여 필터 뱅크의 개수를 33 개에서 17 개로 줄이고 필터 뱅크의 변화량을 2 비트로 할당하는 방식을 사용하였다. 변화량을 비트에 할당하기 위하여 음악 데이터 베이스로부터 추출된 각 밴드의 pmf를 통해 음악의 고유성을 최대로 증진 시킬 수 있는 임계치를 찾아내고 이것을 바탕으로 필터 뱅크의 변화량을 2 비트로 할당하였다. 이 같이 추출된 오디오 핑거프린트를 기반으로 PDA 와 음악 검색기 서버와의 통신을 이용하여 사용자가 요청한 쿼리 음악에 관련된 정보를 제공하는 시스템을 구현했다. 제안된 방식은 다양한 주변 잡음 환경에서 평가되어 기존의 필립스 방식 보다 성능 향상 물론 검색 속도 또한 개선되는 특징을 확인할 수 있었다.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.12
• /
• pp.75-87
• /
• 2009

This paper, which is about the method of creating the audio fingerprint and comparing with the audio data, presents how to distinguish music using the characteristics of audio data. It is a process of applying the Difference of Gaussian (DoG: generally used for recognizing images) to the audio data, and to extract the music that changes radically, and to define the location of fingerprint. This fingerprint is made insensitive to the changes of sound, and is possible to extract the same location of original fingerprint with just a portion of music data. By reducing the data and calculation of fingerprint, this system indicates more efficiency than the pre-system which uses pre-frequency domain. Adopting this, it is possible to indicate the copyrighted music distributed in internet, or meta information of music to users.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2013.06a
• /
• pp.193-195
• /
• 2013

오디오 핑거프린트는 콘텐츠의 오디오 신호의 특색을 요약한 서명(signature)으로 2nd 스크린 서비스의 기반 기술로 주목 받고 있다. 이를 이용한 오디오 핑거프린트 시스템은 콘텐츠의 오디오를 인식하고 해당 콘텐츠와 연관된 메타 데이터를 2nd 디바이스와 웹을 통해 연결시키는 기능을 제공한다. 스마트링크 TV 는 이러한 오디오 핑거프린트를 이용한 KBS 의 콘텐츠 장면(scene) 기반 2nd 스크린 서비스 플랫폼이다. 본 논문에서는 한국의 방송환경에 적용된 스마트링크 TV 의 전반적인 플랫폼 구조와 활용방법에 대해 살펴본다.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.4
• /
• pp.375-382
• /
• 2009

This paper proposes a new audio fingerprinting method based on compressed-domain features. By basing on the compressed domain, the computational efficiency of the proposed method can be greatly enhanced. Especially we deal with MDCT domain, which is widely employed in audio compression, and extract three kinds of subband features; energy, centroid, and flatness. By taking signs after differentially filtering each feature, binary audio fingerprints are obtained. The identification performance of the three kinds of fingerprints are experimentally compared. Among the considered compressed-domain subband features, the subband energy showed the best performance for fingerprinting.

• Journal of Korea Multimedia Society
• /
• v.16 no.4
• /
• pp.453-463
• /
• 2013

In this paper, we present an effective method and a system for the music summarization which automatically extract the chorus portion of a piece of music. A music summary technology is very useful for browsing a song or generating a sample music for an online music service. To develop the solution, conventional automatic music summarization methods use a 2-dimensional similarity matrix, statistical models, or clustering techniques. But our proposed method extracts the music summary by calculating BER(Bit Error Rate) between audio fingerprint blocks which are extracted from a song. But we could directly use an enormous audio fingerprint database which was already saved for a music retrieval solution. This shows the possibility of developing a various of new algorithms and solutions using the audio fingerprint database. In addition, experiments show that the proposed method captures the chorus of a song more effectively than a conventional method.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.4
• /
• pp.151-158
• /
• 2006

In this paper, we proposed a new audio fingerprint extraction method, based on Philips' music retrieval algorithm, which uses the energy difference of neighboring filter-bank and probabilistic characteristics of music. Since Philips method uses too many filter-banks in limited frequency band, it may cause audio fingerprints to be highly sensitive to additive noises and to have too high correlation between neighboring bands. The proposed method improves robustness to noises by reducing the number of filter-banks while it maintains the discriminative power by representing the energy difference of bands with 2 bits where the quantization levels are determined by probabilistic characteristics. The correlation which exists among 4 different levels in 2 bits is not only utilized in similarity measurement. but also in efficient reduction of searching area. Experiments show that the proposed method is not only more robust to various environmental noises (street, department, car, office, and restaurant), but also takes less time for database search than Philips in the case where music is highly degraded.