• The Journal of the Acoustical Society of Korea
• /
• v.39 no.3
• /
• pp.143-149
• /
• 2020

This paper presents the effect of the feature extraction methods used in the audio preprocessing on the classification performance of the Convolutional Neural Networks (CNN). We extract mel spectrogram, log mel spectrogram, Mel Frequency Cepstral Coefficient (MFCC), and delta MFCC from the UrbanSound8K dataset, which is widely used in environmental sound classification studies. Then we scale the data to 3 distributions. Using the data, we test four CNNs, VGG16, and MobileNetV2 networks for performance assessment according to the audio features and scaling. The highest recognition rate is achieved when using the unscaled log mel spectrum as the audio features. Although this result is not appropriate for all audio recognition problems but is useful for classifying the environmental sounds included in the Urbansound8K.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.7
• /
• pp.1487-1494
• /
• 2011

In this paper, a novel genre classification algorithm is proposed for music recommendation system. Especially, to improve the classification accuracy, the band-pass filter for octave-based spectral contrast (OSC) feature is designed considering the psycho-acoustic model and actual frequency range of musical instruments. The GTZAN database including 10 genres was used for 10-fold cross validation experiments. The proposed multiple-octave based OSC produces better accuracy by 2.26% compared with the conventional OSC. The combined feature vector based on the proposed OSC and mel-frequency cepstral coefficient (MFCC) gives even better accuracy.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.5
• /
• pp.12-20
• /
• 1999

In this paper, we compared speaker verification performance of the speech data collected in clean environment and in channel environment. For the improvement of the performance of speaker verification gathered in channel, we have studied on the efficient feature parameters in channel environment and on the preprocessing. Speech DB for experiment is consisted of Korean doublet of numbers, considering the text-prompted system. Speech features including LPCC(Linear Predictive Cepstral Coefficient), MFCC(Mel Frequency Cepstral Coefficient), PLP(Perceptually Linear Prediction), LSP(Line Spectrum Pair) are analyzed. Also, the preprocessing of filtering to remove channel noise is studied. To remove or compensate for the channel effect from the extracted features, cepstral weighting, CMS(Cepstral Mean Subtraction), RASTA(RelAtive SpecTrAl) are applied. Also by presenting the speech recognition performance on each features and the processing, we compared speech recognition performance and speaker verification performance. For the evaluation of the applied speech features and processing methods, HTK(HMM Tool Kit) 2.0 is used. Giving different threshold according to male or female speaker, we compare EER(Equal Error Rate) on the clean speech data and channel data. Our simulation results show that, removing low band and high band channel noise by applying band pass filter(150～3800Hz) in preprocessing procedure, and extracting MFCC from the filtered speech, the best speaker verification performance was achieved from the view point of EER measurement.

• Journal of the Institute of Convergence Signal Processing
• /
• v.7 no.3
• /
• pp.116-121
• /
• 2006

In this paper, we propose the dimension reduction method of multi-dimension speech feature vector for real-time adaptation procedure in various noisy environments. This method which reduces dimensions non-linearly to map the likelihood of speech feature vector and noise feature vector. The LRT(Likelihood Ratio Test) is used for classifying speech and non-speech. The results of implementation are similar to multi-dimensional speech feature vector. The results of speech recognition implementation of detected speech data are also similar to multi-dimensional(10-order dimensional MFCC(Mel-Frequency Cepstral Coefficient)) speech feature vector.

• The Journal of the Acoustical Society of Korea
• /
• v.30 no.2
• /
• pp.100-106
• /
• 2011

Music recordings have been digitalized such that huge size of music database is available to the public. Thus, the automatic classification system of music genres is required to effectively manage the growing music database. Mel-Frequency Cepstral Coefficient (MFCC) is a popular feature vector for genre classification. In this paper, the combined super-vector with Decorrelated Filter Bank (DFB) and Octave-based Spectral Contrast (OSC) using texture windows is processed by Support Vector Machine (SVM) for genre classification. Even with the lower order of the feature vector, the proposed super-vector produces 4.2 % improved classification accuracy compared with the conventional Marsyas system.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.10
• /
• pp.59-66
• /
• 2022

This research conducted a study classifying gender of speakers by analyzing feature vectors extracted from the voice data. The study provides convenience in automatically recognizing gender of customers without manual classification process when they request any service via voice such as phone call. Furthermore, it is significant that this study can analyze frequently requested services for each gender after gender classification using a learning model and offer customized recommendation services according to the analysis. Based on the voice data of males and females excluding blank spaces, the study extracts feature vectors from each data using MFCC(Mel Frequency Cepstral Coefficient) and utilizes SVM(Support Vector Machine) models to conduct machine learning. As a result of gender classification of voice data using a learning model, the gender recognition rate was 94%.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.6
• /
• pp.243-249
• /
• 2007

We propose an effective voice-based gender identification using group delay(GD) Generally, features for speech recognition are composed of magnitude information rather than phase information. In our approach, we address a difference between male and female for GD which is a derivative of the Fourier transform phase. Also, we propose a novel way to incorporate the features fusion scheme based on a combination of GD and magnitude information such as mel-frequency cepstral coefficients(MFCC), linear predictive coding (LPC) coefficients, reflection coefficients and formant. The experimental results indicate that GD is effective in discriminating gender and the performance is significantly improved when the proposed feature fusion technique is applied.

• Phonetics and Speech Sciences
• /
• v.7 no.4
• /
• pp.9-16
• /
• 2015

In this paper, several experiments are performed according to deep neural network (DNN) based features for the performance comparison of speaker verification (SV) systems. To this end, input features for a DNN, such as mel-frequency cepstral coefficient (MFCC), linear-frequency cepstral coefficient (LFCC), and perceptual linear prediction (PLP), are first compared in a view of the SV performance. After that, the effect of a DNN training method and a structure of hidden layers of DNNs on the SV performance is investigated depending on the type of features. The performance of an SV system is then evaluated on the basis of I-vector or probabilistic linear discriminant analysis (PLDA) scoring method. It is shown from SV experiments that a tandem feature of DNN bottleneck feature and MFCC feature gives the best performance when DNNs are configured using a rectangular type of hidden layers and trained with a supervised training method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.473-476
• /
• 2005

This paper is proposed a robust various feature parameters in noise. Feature parameter MFCC(Mel Frequency Cepstral Coefficient) used in conventional speech recognition shows good performance. But, parameter transformed feature space that uses PCA(Principal Component Analysis)and ICA(Independent Component Analysis) that is algorithm transformed parameter MFCC's feature space that use in old for more robust performance in noise is compared with the conventional parameter MFCC's performance. The result shows more superior performance than parameter and MFCC that feature parameter transformed by the result ICA is transformed by PCA.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.8
• /
• pp.3257-3269
• /
• 2020

Articulation disorders are characterized by an inability to achieve clear pronunciation due to misuse of the articulators. In this paper, a method of detecting such disorders by comparing to the standard pronunciations is proposed. This method defines the standard pronunciations from the speeches of normal children by clustering them with three features which are the Linear Predictive Cepstral Coefficient (LPCC), the Mel-Frequency Cepstral Coefficient (MFCC), and the Relative Spectral Analysis Perceptual Linear Prediction (RASTA-PLP). By calculating the distance between the centroid of the standard pronunciation and the inputted pronunciation, disordered speech whose features locates outside the cluster is detected. 89 children (58 of normal children and 31 of children with disorders) were recruited. 35 U-TAP test words were selected and each word's standard pronunciation is made from normal children and compared to each pronunciation of children with disorders. In the experiments, the pronunciations with disorders were successfully distinguished from the standard pronunciations.