Shi-Huang Chen

Audio classification and categorization based on wavelets and support vector Machine

In this paper, an improved audio classification and categorization technique is presented. This technique makes use of wavelets and support vector machines (SVMs) to accurately classify and categorize audio data. When a query audio is given, wavelets are first applied to extract acoustical features such as subband power and pitch information. Then, the proposed method uses a bottom-up SVM over these acoustical features and additional parameters, such as frequency cepstral coefficients, to accomplish audio classification and categorization. A public audio database (Muscle Fish), which consists of 410 sounds in 16 classes, is used to evaluate the performances of the proposed method against other similar schemes. Experimental results show that the classification errors are reduced from 16 (8.1%) to six (3.0%), and the categorization accuracy of a given audio sound can achieve 100% in the Top 2 matches.

Speech Enhancement Using Perceptual Wavelet Packet Decomposition and Teager Energy Operator

It has been shown in the literature that the perceptual wavelet packet decomposition (PWPD) and the Teager energy operator (TEO) are useful for various speech processing systems and speech enhancement applications, respectively. By the use of the PWPD and the TEO, this paper presents an improved wavelet-based speech enhancement method. The main advantage of the proposed method is that the over thresholding of speech segments which is usually occurred in conventional wavelet-based speech enhancement schemes can be avoided. As a consequence, the enhanced speech quality of the proposed method can be increased substantially from those of conventional approaches. In addition, the proposed method does not require a complicated estimation of the noise level or any knowledge of the SNR. Using speech signals corrupted by additive and real noises, experimental results demonstrate that the speech enhancement method presented in this paper is capable of outperforming conventional noise cancellation schemes.

Algebraic Decoding of Quadratic Residue Codes Using Berlekamp-Massey Algorithm *

In this paper, an algebraic decoding method is proposed for the quadratic residue codes that utilize the Berlekamp-Massey algorithm. By a modification of the technique developed by He et al., one can express the unknown syndromes as functions of the known syndromes. The unknown syndromes are determined by an efficient algorithm also developed in this paper. With the appearance of unknown syndromes, one obtains the consecutive syndromes that are needed for the application of the Berlekamp-Massey algorithm. The decoding scheme, developed here, is easier to implement than the previous decoding algorithm developed for the Golay code and the (47, 24, 11) QR code. Moreover, it can be extended to decode all codes of the family of binary quadratic residue codes with irreducible generating polynomials.

Improved voice activity detection algorithm using wavelet and support vector machine

This paper proposes an improved voice activity detection (VAD) algorithm using wavelet and support vector machine (SVM) for European Telecommunication Standards Institution (ETSI) adaptive multi-rate (AMR) narrow-band (NB) and wide-band (WB) speech codecs. First, based on the wavelet transform, the original IIR filter bank and pitch/tone detector are implemented, respectively, via the wavelet filter bank and the wavelet-based pitch/tone detection algorithm. The wavelet filter bank can divide input speech signal into several frequency bands so that the signal power level at each sub-band can be calculated. In addition, the background noise level can be estimated in each sub-band by using the wavelet de-noising method. The wavelet filter bank is also derived to detect correlated complex signals like music. Then the proposed algorithm can apply SVM to train an optimized non-linear VAD decision rule involving the sub-band power, noise level, pitch period, tone flag, and complex signals warning flag of input speech signals. By the use of the trained SVM, the proposed VAD algorithm can produce more accurate detection results. Various experimental results carried out from the Aurora speech database with different noise conditions show that the proposed algorithm gives considerable VAD performances superior to the AMR-NB VAD Options 1 and 2, and AMR-WB VAD.

A wavelet-based voice activity detection algorithm in noisy environments

This paper presents a new voice activity detection (VAD) algorithm based on the perceptual wavelet packet transform (PWPT) and the Teager energy operator (TEO). The basic procedure of the proposed VAD algorithm is to make use of the PWPT to decompose the input speech into critical subband signals. Then a parameter called voice activity shape (VAS) can be derived from the TEO of these critical subband signals. It is shown in this paper that the VAS can be used as a robust feature for VAD. The advantage of this new algorithm is that the preset threshold values or a priori knowledge of the SNR usually needed in conventional VAD methods can be completely avoided. Various experimental results show that the proposed VAD algorithm is capable of outperforming to the ITU-T G.729B VAD and can operate reliably in real noisy environments.

Robust voice activity detection using perceptual wavelet-packet transform and Teager energy operator

In this letter, a robust voice activity detection (VAD) algorithm is presented. This proposed VAD algorithm makes use of the perceptual wavelet-packet transform and the Teager energy operator to compute a robust parameter called voice activity shape for VAD. The main advantage of this algorithm is that the preset threshold values or a priori knowledge of the SNR usually needed in conventional VAD methods can be completely avoided. Various experimental results show that the proposed VAD algorithm is capable of outperforming the VAD of Adaptive Multi Rate (AMR) speech codec in both additive noisy and real noisy environments.

A Near Lossless Wavelet-Based Compression Scheme for Satellite Images

In this paper, a near lossless image compression algorithm is presented for high quality satellite image compression. The proposed algorithm makes use of the recommendation for image data compression from the Consultative Committee for Space Data Systems (CCSDS) and specific residue image bit-plane compensation. Comparing with the recommendation for satellite image compression from CCSDS, the proposed algorithm can reconstruct near lossless images with less bit rate than the recommendation of CCSDS does. Benefited from run-length coding and specific residue image bit-plane compensation, the proposed algorithm can obtain higher quality satellite image at similar bit rate or lower bit rate at the similar image quality. These results are valuable for reducing transmission time of high quality satellite image data. This work can be further improved by combining other binary compression techniques and the extension of this work may offer a VLSI or a DSP implementation of the proposed algorithm. Satellite image transmission and storage system can benefit by the proposed algorithm.

A C/V segmentation algorithm for Mandarin speech signal based on wavelet transforms

This paper proposes a new consonant/vowel (C/V) segmentation algorithm for Mandarin speech signal. Since the Mandarin phoneme structure is a combination of a consonant (may be null) followed by a vowel, the C/V segmentation is an important part in the Mandarin speech recognition system. Based on the wavelet transform, the proposed method can directly search for the C/V segmentation point by using a product function and energy profile. The product function is generated from the appropriate wavelet and scaling coefficients of the input speech signal, and it can be applied to indicate the C/V segmentation point. With this product function and the additional verification of the energy profile, the C/V segmentation can be accurately pointed out with a low computation complexity. Experiments are provided that demonstrate the superior performance of the proposed algorithm. An overall accuracy rate of 97.2% is achieved. This algorithm is suitable for Mandarin speech recognition task.

The Implementation of Real-Time On-line Vehicle Diagnostics and Early Fault Estimation System

This paper developed an intelligent technology for real-time vehicle diagnostics and early fault estimation. The proposed system consists of vehicle on board unit (OBU) and vehicle diagnostics server (VDS). The vehicle OBU and VDS integrate with several subsystems, including vehicle wireless network, global positioning system (GPS), CAN bus, on-board diagnostics (OBD), and online expert system. The vehicle OBU could obtain real-time vehicle operation data, such as speed, engine RPM (Revolution(s) Per Minute), throttle, break, coolant temperature, battery voltage, O2 sensor, fuel trim, instant fuel consumption, and etc., from CAN bus and OBD. These vehicle operation data will be uploaded to the VDS via 3.5G or WiMAX wireless network. Then, the expert system built-in the VDS will analyze these vehicle operation data and perform real-time vehicle diagnostics or fault early warning. Once abnormal conditions have been detected, the VDS will inform deriver or qualified factory of the requirement of vehicle maintenance or repair. Using this system could increase the driving safety as well as decrease the air pollution and unnecessary fuel consumption caused by vehicle faults. This will also benefit our living environment, energy saving, and carbon reduction.

Simplified 2-D Cubic Spline Interpolation Scheme Using Direct Computation Algorithm

It has been shown that the 2-D cubic spline interpolation (CSI) proposed by Truong is one of the best algorithms for image resampling or compression. Such a CSI algorithm together with the image coding standard, e.g., JPEG, can be used to obtain a modified image codec while still maintaining a good quality of the reconstructed image for higher compression ratios. In this paper, a fast direct computation algorithm is developed to improve the computational efficiency of the original FFT-based 2-D CSI methods. In fact, this algorithm computes the 2-D CSI directly without explicitly calculating the complex division usually needed in the FFT or Winograd discrete Fourier transform (WDFT) algorithm. In addition, this paper describes a novel way to derivate the 2-D CSI from the 1-D CSI by using the row-column method. This new fast 2-D CSI provides a regular and simple structure based upon linear correlations. Therefore, it can be implemented by the use of a modification of Kungs pipeline structure and is naturally suitable for VLSI implementations. Experimental results show that the proposed new fast 2-D CSI algorithm can achieve almost the same CSI performance with much fewer arithmetic operations in comparison with existing efficient algorithms.