• MALSORI
• /
• no.61
• /
• pp.63-74
• /
• 2007

Discrimination of music and speech from the multimedia signal is an important task in audio coding and broadcast monitoring systems. This paper deals with the problem of feature parameter extraction for discrimination of music and speech. The wavelet transform is a multi-resolution analysis method that is useful for analysis of temporal and spectral properties of non-stationary signals such as speech and audio signals. We propose new feature parameters extracted from the wavelet transformed signal for discrimination of music and speech. First, wavelet coefficients are obtained on the frame-by-frame basis. The analysis frame size is set to 20 ms. A parameter $E_{sum}$ is then defined by adding the difference of magnitude between adjacent wavelet coefficients in each scale. The maximum and minimum values of $E_{sum}$ for period of 2 seconds, which corresponds to the discrimination duration, are used as feature parameters for discrimination of music and speech. To evaluate the performance of the proposed feature parameters for music and speech discrimination, the accuracy of music and speech discrimination is measured for various types of music and speech signals. In the experiment every 2-second data is discriminated as music or speech, and about 93% of music and speech segments have been successfully detected.

• Proceedings of the IEEK Conference
• /
• 2004.08c
• /
• pp.890-895
• /
• 2004

This paper describes constant alarm rates process of millimeter wave radar that exits on non-stationary target detection schemes in the ground clutter conditions. The comparison of various CFAR processes such as CA(Cell-Average)-CFAR, GO(Greatest Of)/SO(Smallest Of)-CFAR and OS(Order Statistics)-CFAR performance are applied. Using matlab software, we show the performance and loss between detection probability and signal to noise ratio. When rang bins increase, this results show the OS-CFAR process performance is better than any others and satisfies the optimal detection probability without loss of detection in the homogeneous clutter.

• ETRI Journal
• /
• v.36 no.3
• /
• pp.514-517
• /
• 2014

In this paper, alternative dynamic features for speech recognition are proposed. The goal of this work is to improve speech recognition accuracy by deriving the representation of distinctive dynamic characteristics from a speech spectrum. This work was inspired by two temporal dynamics of a speech signal. One is the highly non-stationary nature of speech, and the other is the inter-frame change of a speech spectrum. We adopt the use of a sub-frame spectrum analyzer to capture very rapid spectral changes within a speech analysis frame. In addition, we attempt to measure spectral fluctuations of a more complex manner as opposed to traditional dynamic features such as delta or double-delta. To evaluate the proposed features, speech recognition tests over smartphone environments were conducted. The experimental results show that the feature streams simply combined with the proposed features are effective for an improvement in the recognition accuracy of a hidden Markov model-based speech recognizer.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.58 no.2
• /
• pp.164-171
• /
• 2009

This paper presents new learning algorithm of dynamic Bayesian networks (DBN) by means of constrained least square (LS) estimation algorithm and gradient descent method. First, we propose constrained LS based parameter estimation for a Markov chain (MC) model given observation data sets. Next, a gradient descent optimization is utilized for online estimation of a hidden Markov model (HMM), which is bi-linearly constructed by adding an observation variable to a MC model. We achieve numerical simulations to prove its reliability and superiority in which a series of non stationary random signal is applied for the DBN models respectively.

• Journal of Electrical Engineering and Technology
• /
• v.4 no.2
• /
• pp.168-174
• /
• 2009

An application of wavelet analysis to power system transient generated signals is presented in this paper. With the time-frequency localisation characteristics embedded in wavelets, the time and frequency information of a waveform can be presented as a visualised scheme. This feature is very important for non-stationary signals analysis such as the ones generated from power system disturbances. Unlike the Fourier transform, the wavelet transform approach is more efficient in monitoring fault signals as time varies. For time intervals where the function changes rapidly, this method can zoom in on the area of interest for better visualisation of signal characteristics.

• Structural Engineering and Mechanics
• /
• v.49 no.3
• /
• pp.411-425
• /
• 2014

This paper presents the processing of nonlinear features associated with a damage event by quadratic time-frequency distributions for damage identification in a frame structure. A time-frequency distribution is a function which distributes the total energy of a signal at a particular time and frequency point. As the occurrence of damage often gives rise to non-stationary, nonlinear structural behavior, simultaneous representation of the dynamic response in the time-frequency plane offers valuable insight for damage detection. The applicability of the bilinear time-frequency distributions of the Cohen class is examined for the damage assessment of a frame structure from the simulated acceleration data. It is shown that the changes in instantaneous energy of the dynamic response could be a good damage indicator. Presence and location of damage can be identified using Choi-Williams distribution when damping is ignored. However, in the presence of damping the Page distribution is more effective and offers better readability for structural damage detection.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2005.11b
• /
• pp.144-147
• /
• 2005

The tire is considered as one of the Important noise sources having an influence on vehicle's performance. The Pattern noise of a tire is the transmission sound of airborne noise. On smooth asphalt road, Pattern noise is amplified with the velocity. In recent, the study on the reduction of Pattern noise is energetically processed. Pattern noise is strongly related with pitch sequence. To reduce the pattern noise, tire's designer has to randomize the sequence of pitch. The FFT is a traditional method to evaluate the level of the randomization of the pitch sequence, but gives no information on time-varying, instantaneous frequency. In the study, we found that Time-Frequency transform is a useful method to non-stationary signal such as tire noise.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2002.10a
• /
• pp.453-458
• /
• 2002

A recently developed Hilbert-Huang transform (HHT) technique is applied to the detection of the damage locations of bridge structures. The HHT may be used to identify the locations of damages which exhibit nonlinear and non-stationary behavior, since the instantaneous frequency characteristics of the measured signal can be analyzed by the HHT. Numerical simulations were conducted on two bridge systems with damages using controlled excitations with sweeping frequency. Nonlinear plastic model using a gap element is employed to model the behavior of the cracked elements in the numerical simulations. The results indicate that the HHT method can reasonably identify the damage locations based on a limited number of acceleration sensors. Experimental study has been 실so carried out on a steel frame to confirm the applicability of the HHT to detect a structural connection with loosened bolts.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2003.05a
• /
• pp.827-832
• /
• 2003

There has been a number methods for the presentation of time-frequency analysis of non-stationary signal. In this paper, STFT(short time Fourier transform), wavelet transform, Wigner distribution, and higher order Wigner distribution are discussed in details with simulation signals. They are also applied to the analysis of the wave propagation of a semi finite beam. Wigner distribution and higher order Wigner distribution have good time-frewuency resolutions. Wavelet transform is required for impact analysis but should be applied carefully. STFT suffers from time-frequency resolutions. Each method is has its advantage and disadvantage depending on each application signals.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.345-346
• /
• 2006

In this paper, we propose the noise suppressor with the psychoacoustic model and wavelet packet transform. The objective of the scheme is to enhance speech corrupted by colored or non-stationary noise. If corrupted noise is colored, subband approach would be more efficient than whole band one. To avoid serious residual noise and speech distortion, we must adjust the Wavelet Coefficient threshold. In this paper, the subband is designed matching with the critical band. And WCT is adapted by noise masking threshold(NMT) and segmental signal to noise ratio(seg_SNR). Consequently this work improve the PESQ-MOS about 0.23 in the case of coded speech.