• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.1
• /
• pp.333-342
• /
• 2012

This paper presents a vowel onset point (VOP) detection method based on the human auditory system. This method maps the "perceptual" frequency scale, i.e. Mel scale onto a linear acoustic frequency, and then establishes a series of Triangular Mel-weighted Filter Bank simulate the function of band pass filtering in human ear. This nonlinear critical-band filter bank helps greatly reduce the data dimensionality, and eliminate the effect of harmonic waves to make the formants more prominent in the nonlinear spaced Mel spectrum. The sum of mel spectrum peaks energy is extracted as feature for each frame, and the instinct at which the energy amplitude starts rising sharply is detected as VOP, by convolving with Gabor window. For the single-word database which contains 12 vowels articulated with different kinds of consonants, the experimental results showed a good average detection rate of 72.73%, higher than other vowel detection methods based on short-time energy and zero-crossing rate.

• Journal of Korea Society of Industrial Information Systems
• /
• v.6 no.4
• /
• pp.81-88
• /
• 2001

In this paper, a Korean digit recognition system based on a multilayer Perceptron is implemented. We also investigate the performance of widely used speech features, such as the Mel-scale filterbank, MFCC, LPCC, and PLP coefficients, by applying them as input of the proposed recognition system. In order to build a robust speech system, the experiments for demonstrating its recognition performance for the clean data as well as corrupt data are carried out. In experiments of recognizing 20 Korean digit, we found that the Mel-scale filterbank coefficients performs best in terms of recognition accuracy for the speech dependent and speech independent database even though noise is considerably added.

• Speech Sciences
• /
• v.14 no.4
• /
• pp.131-144
• /
• 2007

In an effort to improve the performance of mel frequency cepstral coefficients (MFCC), we investigate the effects of varying the parameters for the filter banks and their associated windows on speech recognition rates. Specifically, the mel and bark scales are combined with various types of filter bank windows. Comparison and evaluation of the suggested methods are performed by two independent ways of speech recognition and the Fisher discriminant objective function. It is shown that the Hanning window based on the bark scale yields 28.1% relative performance improvements over the triangular window with the mel scale in speech recognition error rate. Further work on incorporating PCA and/or LDA would be desirable as a postprocessor to MFCC extraction.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.15 no.5
• /
• pp.227-234
• /
• 2020

In this paper, we propose wav-U-Net to improve speech enhancement in heavy noisy environments, and it has implemented three principal techniques. First, as input data, we use 128 modified Mel-scale filter banks which can reduce computational burden instead of 512 frequency bins. Mel-scale aims to mimic the non-linear human ear perception of sound by being more discriminative at lower frequencies and less discriminative at higher frequencies. Therefore, Mel-scale is the suitable feature considering both performance and computing power because our proposed network focuses on speech signals. Second, we add a simple ResNet as pre-processing that helps our proposed network make estimated speech signals clear and suppress high-frequency noises. Finally, the proposed U-Net model shows significant performance regardless of the kinds of noise. Especially, despite using a single channel, we confirmed that it can well deal with non-stationary noises whose frequency properties are dynamically changed, and it is possible to estimate speech signals from noisy speech signals even in extremely noisy environments where noises are much lauder than speech (less than SNR 0dB). The performance on our proposed wav-U-Net was improved by about 200% on SDR and 460% on NSDR compared to the conventional Jansson's wav-U-Net. Also, it was confirmed that the processing time of out wav-U-Net with 128 modified Mel-scale filter banks was about 2.7 times faster than the common wav-U-Net with 512 frequency bins as input values.

• Phonetics and Speech Sciences
• /
• v.7 no.4
• /
• pp.27-33
• /
• 2015

This paper proposes an audio event classification method using Deep Neural Networks (DNN). The proposed method applies Feed Forward Neural Network (FFNN) to generate event probabilities of ten audio events (dog barks, engine idling, and so on) for each frame. For each frame, mel scale filter bank features of its consecutive frames are used as the input vector of the FFNN. These event probabilities are accumulated for the events and the classification result is determined as the event with the highest accumulated probability. For the same dataset, the best accuracy of previous studies was reported as about 70% when the Support Vector Machine (SVM) was applied. The best accuracy of the proposed method achieves as 79.23% for the UrbanSound8K dataset when 80 mel scale filter bank features each from 7 consecutive frames (in total 560) were implemented as the input vector for the FFNN with two hidden layers and 2,000 neurons per hidden layer. In this configuration, the rectified linear unit was suggested as its activation function.

• 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.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.1
• /
• pp.36-42
• /
• 2006

A Principal component analysis (PCA)-based Mel-Frequency Discrete Wavelet Coefficients (MFDWC) feature Parameters for speaker verification system is Presented in this Paper In this method, we used the 1st-eigenvector obtained from PCA to calculate the energy of each node of level that was approximated by. met-scale. This eigenvector satisfies the constraint of general weighting function that the squared sum of each component of weighting function is unity and is considered to represent speaker's characteristic closely because the 1st-eigenvector of each speaker is fairly different from the others. For verification. we used Universal Background Model (UBM) approach that compares claimed speaker s model with UBM on frame-level. We performed experiments to test the effectiveness of PCA-based parameter and found that our Proposed Parameters could obtain improved average Performance of $0.80\%$compared to MFCC. $5.14\%$ to LPCC and 6.69 to existing MFDWC.

• Proceedings of the KAIS Fall Conference
• /
• 2010.05a
• /
• pp.261-264
• /
• 2010

Fast algorithm is proposed by using mel scale and the distribution characteristic of LSP parameters, and is to reduce the computational amount. Computational amount means the calculating times of transformation from LPC coefficients to LSP parameters. Among conventional methods, the real root method is considerably simpler than other, but neverthless, it still suffer from its indeterministic computational time. Because the root searching is processed sequentially in frequency region. In this paper, the searching interval is arranged by using mel scale but not it is uniform and searching order is arranged by the distribution characteristic of LSP parameters that is most LSP papameters are occured in specific frequency region. In experimental results, computational amount of the proposed algorithm is reduced about 48.95% in average, but the transformed LSP parameters of the proposed method were the same as those of real root method.

• Journal of the Institute of Electronics Engineers of Korea TE
• /
• v.42 no.4
• /
• pp.41-46
• /
• 2005

Acoustic problems in the environment have gained attention due to the noise and vibration contact often in industry as well as life on modem society. Noise is one of safety element in industry, this proves damaging to humans from both a physical and a psychological aspect and so drop working efficiency. Various noises are happened from machines of manufacturing process in PCB industry. This paper present a new approach for subband feedback Active Noise Control (ANC) using Mel scale for headset system in PCB industry. The proposed Mel scale subband algorithm had a performance advantage over the subband algorithm in the noise attenuation and convergence time.

• Journal of the Institute of Convergence Signal Processing
• /
• v.9 no.2
• /
• pp.121-128
• /
• 2008

Accurate voice activity detection have a great impact on performance of speech applications including speech recognition, speech coding, and speech communication. In this paper, we propose methods for voice activity detection that can adapt to various car noise situations during driving. Existing voice activity detection used various method such as time energy, frequency energy, zero crossing rate, and spectral entropy that have a weak point of rapid. decline performance in noisy environments. In this paper, the approach is based on existing spectral entropy for VAD that we propose voice activity detection method using MFB(Met-frequency filter banks) spectral entropy, gradient FFT(Fast Fourier Transform) spectral entropy. and gradient MFB spectral entropy. FFT multiplied by Mel-scale is MFB and Mel-scale is non linear scale when human sound perception reflects characteristic of speech. Proposed MFB spectral entropy method clearly improve the ability to discriminate between speech and non-speech for various in noisy car environments that achieves 93.21% accuracy as a result of experiments. Compared to the spectral entropy method, the proposed voice activity detection gives an average improvement in the correct detection rate of more than 3.2%.