S. Krishnan

Discrimination of pathological voices using a time-frequency approach

Acoustical measures of vocal function are routinely used in the assessments of disordered voice, and for monitoring the patients progress over the course of voice therapy. Typically, acoustic measures are extracted from sustained vowel stimuli where short-term and long-term perturbations in fundamental frequency and intensity, and the level of glottal noise are used to characterize the vocal function. However, acoustic measures extracted from continuous speech samples may well be required for accurate prediction of abnormal voice quality that is relevant to the clients real world experience. In contrast with sustained vowel research, there is relatively sparse literature on the effectiveness of acoustic measures extracted from continuous speech samples. This is partially due to the challenge of segmenting the speech signal into voiced, unvoiced, and silence periods before features can be extracted for vocal function characterization. We propose a joint time-frequency approach for classifying pathological voices using continuous speech signals that obviates the need for such segmentation. The speech signals were decomposed using an adaptive time-frequency transform algorithm, and several features such as the octave max, octave mean, energy ratio, length ratio, and frequency ratio were extracted from the decomposition parameters and analyzed using statistical pattern classification techniques. Experiments with a database consisting of continuous speech samples from 51 normal and 161 pathological talkers yielded a classification accuracy of 93.4%.

Adaptive time-frequency analysis of knee joint vibroarthrographic signals for noninvasive screening of articular cartilage pathology

Vibroarthrographic (VAG) signals emitted by human knee joints are nonstationary and multicomponent in nature; time-frequency distributions (TFDs) provide powerful means to analyze such signals. The objective of this paper is to construct adaptive TFDs of VAG signals suitable for feature extraction. An adaptive TFD was constructed by minimum cross-entropy optimization of the TFD obtained by the matching pursuit decomposition algorithm. Parameters of VAG signals such as energy, energy spread. frequency, and frequency spread were extracted from their adaptive TFDs. The parameters carry information about the combined TF dynamics of the signals. The mean and standard deviation of the parameters were computed, and each VAG signal was represented by a set of just six features. Statistical pattern classification experiments based on logistic regression analysis of the parameters showed an overall normal/abnormal screening accuracy of 68.9% with 90 VAG signals (51 normals and 39 abnormals), and a higher accuracy of 77.5% with a database of 71 signals with 51 normals and 20 abnormals of a specific type of patellofemoral disorder. The proposed method of VAG signal analysis is independent of joint angle and clinical information, and shows good potential for noninvasive diagnosis and monitoring of patellofemoral disorders such as chondromalacia patella.

Parametric representation and screening of knee joint vibroarthrographic signals

The authors have been investigating analysis of knee joint vibration or vibroarthrographic (VAG) signals as a potential tool for noninvasive diagnosis and monitoring of cartilage pathology. In this paper, they present a comprehensive comparative study of different parametric representations of VAG signals. Dominant poles and cepstral coefficients were derived from autoregressive models of adaptively segmented VAG signals. Signal features and a few clinical features were used as feature vectors in pattern classification experiments based on logistic regression analysis and the leave-one-out method. The results using 51 normal and 39 abnormal signals indicated the superior performance of cepstral coefficients in VAG signal classification with an accuracy rate of 75.6%. With 51 normal and 20 abnormal signals limited to chondromalacia patella, cepstral coefficients again gave the highest accuracy rate of 85.9%.

Content based audio classification and retrieval using joint time-frequency analysis

We present an audio classification and retrieval technique that exploits the non-stationary behavior of music signals and extracts features that characterize their spectral change over time. Audio classification provides a solution to incorrect and inefficient manual labelling of audio files on computers by allowing users to extract music files based on content similarity rather than labels. In our technique, classification is performed using time-frequency analysis and sounds are classified into 6 music groups consisting of rock, classical, folk, jazz and pop. For each 5 second music segment, the features that are extracted include entropy, centroid, centroid ratio, bandwidth, silence ratio, energy ratio, and location of minimum and maximum energy. Using a database of 143 signals, a set of 10 time-frequency features are extracted and an accuracy of classification of around 93% using regular linear discriminant analysis or 92.3% using the leave-one-out method is achieved.

Adaptive filtering, modelling and classification of knee joint vibroarthrographic signals for non-invasive diagnosis of articular cartilage pathology.

Interpretation of vibrations or sound signals emitted from the patellofemoral joint during movement of the knee, also known as vibroarthrography (VAG), could lead to a safe, objective, and non-invasive clinical tool for early detection, localisation, and quantification of articular cartilage disorders. In this study with a reasonably large database of VAG signals of 90 human knee joints (51 normal and 39 abnormal), a new technique for adaptive segmentation based on the recursive least squares lattice (RLSL) algorithm was developed to segment the non-stationary VAG signals into locally-stationary components; the stationary components were then modelled autoregressively, using the Burg-Lattice method. Logistic classification of the primary VAG signals into normal and abnormal signals (with no restriction on the type of cartilage pathology) using only the AR coefficients as discriminant features provided an accuracy of 68.9% with the leave-one-out method. When the abnormal signals were restricted to chondromalacia patella only, the classification accuracy rate increased to 84.5%. The effects of muscle contraction interference (MCI) on VAG signals were analysed using signals from 53 subjects (32 normal and 21 abnormal), and it was found that adaptive filtering of the MCI from the primary VAG signals did not improve the classification accuracy rate. The results indicate that VAG is a potential diagnostic tool for screening for chondromalacia patella.

Radio over multimode fiber for wireless access

A radio over fiber link is a promising technology for antenna remoting applications. Typically, the radio over fiber link employs a single mode fiber. However, the signal power at the remote antenna is very small. The main reason is large power loss in the E/O and O/E convertor, but the coupling efficiency of a E/O convertor can be improved with multimode fiber (MMF), so we propose to use a ROF link with a vertical-cavity surface-emitting laser with a graded index MMF to transport optical signals. A multimode fiber has a larger core radius compared to a SMF. A larger core radius allows more optical power coupled into a fiber. With simple butt-coupling techniques, the coupling efficiency can be 90% and simplicity leads to reduction in cost of the link. Normally, the MMF is used in short distance digital applications with a bandwidth distance product of about 500 MHz.km, so it is good for local area picocells. Our approach is to transmit passband signals such as QPSK and FSK through the ROF link. Our simulation shows that a 900 MHz carrier can transport through a link of 1.22 km long. In this paper, we investigate the feasibility of using a MMF for antenna remoting in local area picocells and compare the tradeoff between coupling efficiency and bandwidth.

Robust audio watermarking using a chirp based technique

In this study, we propose a new spread spectrum audio watermarking algorithm that embeds linear chirps as watermark messages. Different chirp rates, i.e., slopes on the time-frequency (TF) plane, represent watermark messages such that each slope corresponds to a different message. We extract the watermark message using a line detection algorithm based on the Hough-Radon transform (HRT). The HRT detects the directional elements that satisfy a parametric constraint in the image of a TF plane. The proposed method not only detects the presence of watermark, but also extracts the embedded watermark bits and ensures the message is received correctly. The results show that the HRT detects the embedded watermark message even after common signal processing operations such as MPEG audio coding, resampling, lowpass filtering and amplitude re-scaling.

Detection of chirp and other components in the time-frequency plane using the Hough and Radon transforms

We propose a novel approach to detect chirp (linear frequency modulated) components in multicomponent nonstationary signals in the time-frequency (TF) plane. The approach, based on the Hough and Radon transforms of TF distributions, can be used to detect chirp components with varying energy in unknown signal-to-noise ratio environments. In addition to detection of chirps, the proposed technique could also be used as a tool to evaluate the TF resolution provided by different TF analysis methods.

Fixed block-based lossless compression of digital mammograms

Breast cancer is a leading cause of death among women in Canada. Computer-aided diagnosis of mammograms (X-ray films of breast tissue) is a noninvasive and an inexpensive way of diagnosing breast cancer. The objective of this project is to investigate image compression schemes for faithful transmission and reproduction of digital mammography data over a communication link. A fixed block-based (FBB) near lossless compression scheme for mammograms has been developed which runs in conjunction with traditional compression schemes such as Huffman coding and Lempel-Ziv Welch (1978) coding. The algorithm codes blocks of pixels within the image that contain the same intensity value (the odds of having blocks of the same pixel values in a mammography image are very high), thus reducing the size of the image substantially while encoding the image at the same time. The proposed compression scheme was applied on 44 mammograms (22 benign and 22 malignant), and the compression scheme provided a compression ratio of 1.7:1. When Huffman (1952) coding and LZW coding were used in conjunction with the FBB compression scheme, the compression ratio was 3.81:1 for Huffman, and 5:1 for LZW coding. The proposed FBB lossless compression technique seems to be promising for teleradiology applications.

Denoising knee joint vibration signals using adaptive time-frequency representations

A novel denoising method for improving the signal-to-noise ratio (SNR) of knee joint vibration signals (also known as vibroarthrographic or VAG signals) is proposed. The denoising methods considered are based on signal decomposition techniques such as wavelets, wavelet packets, and the matching pursuit method. Performance evaluation with synthetic signals simulated with characteristics expected of VAG signals indicated good denoising results with the matching pursuit method. Nonstationary signal features extracted and identified from time-frequency distributions of denoised VAG signals have shown good potential in screening for articular cartilage pathology.