• Journal of Information Processing Systems
• /
• v.20 no.1
• /
• pp.13-23
• /
• 2024

Music brings pleasure and relaxation to people. Therefore, it is necessary to classify musical genres based on scenes. Identifying favorite musical genres from massive music data is a time-consuming and laborious task. Recent studies have suggested that machine learning algorithms are effective in distinguishing between various musical genres. However, meeting the actual requirements in terms of accuracy or timeliness is challenging. In this study, a hybrid machine learning model that combines a deep residual auto-encoder (DRAE) and support vector machine (SVM) for musical genre recognition was proposed. Eight manually extracted features from the Mel-frequency cepstral coefficients (MFCC) were employed in the preprocessing stage as the hybrid music data source. During the training stage, DRAE was employed to extract feature maps, which were then used as input for the SVM classifier. The experimental results indicated that this method achieved a 91.54% F1-score and 91.58% top-1 accuracy, outperforming existing approaches. This novel approach leverages deep architecture and conventional machine learning algorithms and provides a new horizon for musical genre classification tasks.

• The Journal of the Acoustical Society of Korea
• /
• v.36 no.6
• /
• pp.401-406
• /
• 2017

This paper presents the performance assessment of several key algorithms conducted for amphibian species sound classification. Firstly, 9 target species including endangered species are defined and a database of their sounds is built. For performance assessment, three feature vectors such as MFCC (Mel Frequency Cepstral Coefficient), RCGCC (Robust Compressive Gammachirp filterbank Cepstral Coefficient), and SPCC (Subspace Projection Cepstral Coefficient), and three classifiers such as GMM(Gaussian Mixture Model), SVM(Support Vector Machine), DBN-DNN(Deep Belief Network - Deep Neural Network) are considered. In addition, i-vector based classification system which is widely used for speaker recognition, is used to assess for this task. Experimental results indicate that, SPCC-SVM achieved the best performance with 98.81 % while other methods also attained good performance with above 90 %.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.1
• /
• pp.85-94
• /
• 2017

In this paper, I proposed a sound model generation and a most frequent model search algorithm for recognizing animal vocalization. The sound model generation algorithm generates a optimal set of models through repeating processes such as the training process, the Viterbi Search process, and the most frequent model search process while adjusting HMM(Hidden Markov Model) structure to improve global recognition rate. The most frequent model search algorithm searches the list of models produced by Viterbi Search Algorithm for the most frequent model and makes it be the final decision of recognition process. It is implemented using MFCC(Mel Frequency Cepstral Coefficient) for the sound feature, HMM for the model, and C# programming language. To evaluate the algorithm, a set of animal sounds for 27 species were prepared and the experiment showed that the sound model generation algorithm generates 27 HMM models with 97.29 percent of recognition rate.

• Journal of Broadcast Engineering
• /
• v.23 no.4
• /
• pp.519-525
• /
• 2018

This paper deals with noise suppression of multi-channel data captured by microphone array using multi-channel Wiener filter. Multi-channel Wiener filter does not rely on information about the direction of the target speech and can be partitioned into an MVDR (Minimum Variance Distortionless Response) spatial filter and a single channel spectral filter. The acoustic transfer function between the single speech source and microphones can be estimated by subspace decomposition of multi-channel Wiener filter. The errors are incurred in the estimation of the acoustic transfer function due to the errors in the estimation of correlation matrices, which in turn results in speech distortion in the MVDR filter. To alleviate the speech distortion in the MVDR filter, diagonal loading is applied. In the experiments, database with seven microphones was used and MFCC distance was measured to demonstrate the effectiveness of the diagonal loading.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.5
• /
• pp.2402-2409
• /
• 2011

The voice has distinguishable acoustic properties of speaker as well as transmitting information. The speaker recognition is the method to figures out who speaks the words through acoustic differences between speakers. The speaker recognition is roughly divided two kinds of categories: speaker verification and identification. The speaker verification is the method which verifies speaker himself based on only one's voice. Otherwise, the speaker identification is the method to find speaker by searching most similar model in the database previously consisted of multiple subordinate sentences. This paper composes feature vector from extracting MFCC coefficients and uses the dynamic time warping algorithm to compare the similarity between features. In order to describe common characteristic based on phonological features of spoken words, two subordinate sentences for each speaker are used as the training data. Thus, it is possible to identify the speaker who didn't say the same word which is previously stored in the database.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.5
• /
• pp.31-36
• /
• 2011

In this paper, Mel-Frequency Cepstral Coefficient (MFCC), Decorrelated Filter Bank (DFB), Octave-based Spectral Contrast (OSC), Zero-Crossing Rate (ZCR), and Spectral Contract/Roll-Off are combined as a set of multiple feature-vectors for the music genre classification system based on the Support Vector Machine (SVM) classifier. In the conventional system, feature vectors for the entire genre classes are normalized for the SVM model training and classification. However, in this paper, selected feature vectors that are compared based on the One-Against-One (OAO) SVM classifier are only used for normalization. Using OSC as a single feature-vector and the multiple feature-vectors, we obtain the genre classification rates of 60.8% and 77.4%, respectively, with the conventional normalization method. Using the proposed normalization method, we obtain the increased classification rates by 8.2% and 3.3% for OSC and the multiple feature-vectors, respectively.

• Journal of Broadcast Engineering
• /
• v.20 no.3
• /
• pp.408-413
• /
• 2015

Recently, According to increasing interest to original sound Karaoke instrument, MIDI type karaoke manufacturer attempt to make more cheap method instead of original recoding method. The specific method is to make the original sound accompaniment to remove only the voice of the singer in the singer music album. In this paper, a system to separate vocal components from music accompaniment for stereo recordings were proposed. Proposed system consists of two stages. The first stage is a vocal detection. This stage classifies an input into vocal and non vocal portions by using SVM with MFCC. In the second stage, selective frequency subtractions were performed at each frequency bin in vocal portions. In this case, it is determined in consideration not only the energies for each frequency bin but also the phase of the each frequency bin at each channel signal. Listening test with removed vocal music from proposed system show relatively high satisfactory level.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.12
• /
• pp.238-244
• /
• 2013

For musical genre classification, various types of feature vectors are utilized. Mel-frequency cepstral coefficient (MFCC), decorrelated filter bank (DFB), and octave-based spectral contrast (OSC) are widely used as short-term features, and their long-term variations are also utilized. In this paper, OSC features are extracted not only in the single-octave band domain, but also in the multiple-octave band one to capture the correlation between octave bands. As a baseline system, we select the genre classification system that won the fourth place in the 2012 music information retrieval evaluation exchange (MIREX) contest. By applying the OSC features based on multiple-octave bands, we obtain the better classification accuracy by 0.40% and 3.15% for the GTZAN and Ballroom databases, respectively.

• 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.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.5
• /
• pp.361-367
• /
• 2016

The intruder detection system using digital PIR sensor has the problem that it can't recognize human correctly. In this paper, we suggest a new intruder detection system based on analog PIR sensor to get around the drawbacks of the digital PIR sensor. The analog type PIR sensor emits the voltage output at various levels whereas the output of the digitial PIR sensor is binary. The signal captured using analog PIR sensor is sampled, and its frequency feature is extracted using FFT or MFCC. The extracted features are used for the input of neural networks. After neural network is trained using various human and pet's intrusion data, it is used for classifying human and pet in the intrusion situation.