• Journal of Korea Multimedia Society
• /
• v.10 no.11
• /
• pp.1398-1406
• /
• 2007

Providing natural and efficient access to the fast growing multimedia information is a critical aspect for content-based information system. Query by humming system allows the user to find a song by humming part of the tune form music database. Conventional music information retrieval systems use a high precision pitch extraction method. However, it is very difficult to extract true pitch perfectly. So, In this paper, we propose to use YIN parameter with applying the reliability to reduce the pitch extraction errors. And we describes developed music information retrieval method based on a query by humming system which uses reliable feature extraction. Developed system is based on a continuous dynamic programming algorithm with features including pitch, duration and energy along with their confidence measures. The experiment showed that the proposed method could reduce the errors of the top-10 7.2% and the top-1 9.1% compared with the cepsturm based multiple pitch candidate. The overall retrieval system achieved 92.8% correct retrieval in the top-10 rank list on a database of 155 songs.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.5
• /
• pp.109-116
• /
• 2010

In this paper, we propose a method for extracting predominant melody of polyphonic music based on harmonic structure. Since polyphonic music contains multiple sound sources, the process of melody detection consists of extraction of multiple fundamental frequencies and determination of predominant melody using those fundamental frequencies. Harmonic structure is an important feature parameter of monophonic signal that has spectral peaks at the integer multiples of its fundamental frequency. We extract all fundamental frequency candidates contained in the polyphonic signal by verifying the required condition of harmonic structure. Then, we combine those harmonic peaks corresponding to each extracted fundamental frequency and assign a rank to each after calculating its harmonic average energy. We finally run pitch tracking based on the rank of extracted fundamental frequency and continuity of fundamental frequency, and determine the predominant melody. We measure the performance of proposed method using ADC 2004 DB and 100 Korean pop songs in terms of MIREX 2005 evaluation metrics, and pitch accuracy of 90.42% is obtained.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.6
• /
• pp.600-605
• /
• 2020

In this paper, we propose a sound event detection method using a multi-channel multi-scale neural networks for sound sensing home monitoring for the hearing impaired. In the proposed system, two channels with high signal quality are selected from several wireless microphone sensors in home. The three features (time difference of arrival, pitch range, and outputs obtained by applying multi-scale convolutional neural network to log mel spectrogram) extracted from the sensor signals are applied to a classifier based on a bidirectional gated recurrent neural network to further improve the performance of sound event detection. The detected sound event result is converted into text along with the sensor position of the selected channel and provided to the hearing impaired. The experimental results show that the sound event detection method of the proposed system is superior to the existing method and can effectively deliver sound information to the hearing impaired.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.10C
• /
• pp.965-974
• /
• 2007

In this paper, we proposed the feature selection algorithm for multi-class genre classification. In our proposed algorithm, we developed GMM separation score based on Gaussian mixture model for measuring separability between two genres. Additionally, we improved feature subset selection algorithm based on sequential forward selection for multi-class genre classification. Instead of setting criterion as entire genre separability measures, we set criterion as worst genre separability measure for each sequential selection step. In order to assess the performance proposed algorithm, we extracted various features which represent characteristics such as timbre, rhythm, pitch and so on. Then, we investigate classification performance by GMM classifier and k-NN classifier for selected features using conventional algorithm and proposed algorithm. Proposed algorithm showed improved performance in classification accuracy up to 10 percent for classification experiments of low dimension feature vector especially.

• Science of Emotion and Sensibility
• /
• v.16 no.1
• /
• pp.117-124
• /
• 2013

This study examined that how precisely MFCC, LPC, energy, and pitch related parameters of the speech data, which have been used mainly for voice recognition system could predict the vocal emotion categories as well as dimensions of vocal emotion. 110 college students participated in this experiment. For more realistic emotional response, we used well defined emotion-inducing stimuli. This study analyzed the relationship between the parameters of MFCC, LPC, energy, and pitch of the speech data and four emotional dimensions (valence, arousal, intensity, and potency). Because dimensional approach is more useful for realistic emotion classification. It results in the best vocal cue parameters for predicting each of dimensions by stepwise multiple regression analysis. Emotion categorizing accuracy analyzed by LDA is 62.7%, and four dimension regression models are statistically significant, p<.001. Consequently, this result showed the possibility that the parameters could also be applied to spontaneous vocal emotion recognition.

• 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.