A Hybrid Architecture for Recognising Speech Signals in Malayalam

Speech is the primary, most prominent and convenient means of communication in audible language. Through speech, people can express their thoughts, feelings or perceptions by the articulation of words. Human speech is a complex signal which is non stationary in nature. It consists of immensely rich information about the words spoken, accent, attitude of the speaker, expression, intention, sex, emotion as well as style. The main objective of Automatic Speech Recognition (ASR) is to identify whatever people speak by means of computer algorithms. This enables people to communicate with a computer in a natural spoken language. Automatic recognition of speech by machines has been one of the most exciting, significant and challenging areas of research in the field of signal processing over the past five to six decades. Despite the developments and intensive research done in this area, the performance of ASR is still lower than that of speech recognition by humans and is yet to achieve a completely reliable performance level. The main objective of this thesis is to develop an efficient speech recognition system for recognising speaker independent isolated words in Malayalam.

The relation between intelligibility and the acoustic characteristics of deaf speech: An acoustic analysis of the vowels /i/ and /aw/, and nasals

This paper discusses a study that examined acoustic measures and the relationship to speech intelligibility of children with cochlear implants.

Invasive neural prosthesis for neural signal detection and nerve stimulation

This paper specifically examines the implantation of a microelectrode array into the median nerve of the left arm of a healthy male volunteer. The objective was to establish a bi-directional link between the human nervous system and a computer, via a unique interface module. This is the first time that such a device has been used with a healthy human. The aim of the study was to assess the efficacy, compatibility, and long term operability of the neural implant in allowing the subject to perceive feedback stimulation and for neural activity to be detected and processed such that the subject could interact with remote technologies. A case study demonstrating real-time control of an instrumented prosthetic hand by means of the bi-directional link is given. The implantation did not result in infection, and scanning electron microscope images of the implant post extraction have not indicated significant rejection of the implant by the body. No perceivable loss of hand sensation or motion control was experienced by the subject while the implant was in place, and further testing of the subject following the removal of the implant has not indicated any measurable long term defects. The implant was extracted after 96 days. Copyright © 2004 John Wiley & Sons, Ltd.

Detecting the number of signals using antenna array: a single threshold solution

A new approach is presented to identify the number of incoming signals in antenna array processing. The new method exploits the inherent properties existing in the noise eigenvalues of the covariance matrix of the array output. A single threshold has been established concerning information about the signal and noise strength, data length, and array size. When the subspace-based algorithms are adopted the computation cost of the signal number detector can almost be neglected. The performance of the threshold is robust against low SNR and short data length.

Time-frequency analysis of acoustic noise produced by breaking of crisp biscuits

This paper demonstrates by means of joint time-frequency analysis that the acoustic noise produced by the breaking of biscuits is dependent on relative humidity and water activity. It also shows that the time-frequency coefficients calculated using the adaptive Gabor transformation algorithm is dependent on the period of time a biscuit is exposed to humidity. This is a new methodology that can be used to assess the crispness of crisp foods. (c) 2007 Elsevier Ltd. All rights reserved.

Comparative Analysis of Objective Distortion Measures for Speech Signals Degraded by Noise

Speech signals degraded by additive noise can affects different applications in telecommunication. The noise may degrades the intelligibility of the speech signals and its waveforms as well. In some applications such as speech coding, both intelligibility and waveform quality are important but only intelligibility has been focused lastly. So, modern speech quality measurement techniques such as PESQ (Perceptual Evaluation of Speech Quality) have been used and classical distortion measurement techniques such as Cepstral Distance are becoming unused. In this paper it is shown that some classical distortion measures are still important in applications where speech corrupted by additive noise has to be evaluated.

Neural network detection of grinding burn from acoustic emission

An artificial neural network (ANN) approach is proposed for the detection of workpiece `burn', the undesirable change in metallurgical properties of the material produced by overly aggressive or otherwise inappropriate grinding. The grinding acoustic emission (AE) signals for 52100 bearing steel were collected and digested to extract feature vectors that appear to be suitable for ANN processing. Two feature vectors are represented: one concerning band power, kurtosis and skew; and the other autoregressive (AR) coefficients. The result (burn or no-burn) of the signals was identified on the basis of hardness and profile tests after grinding. The trained neural network works remarkably well for burn detection. Other signal-processing approaches are also discussed, and among them the constant false-alarm rate (CFAR) power law and the mean-value deviance (MVD) prove useful.

Common architecture for discrete wavelet transform analysis and synthesis with sequential and constant processing elements

This paper adresses the problem on processing biological data such as cardiac beats, audio and ultrasonic range, calculating wavelet coefficients in real time, with processor clock running at frequency of present ASIC's and FPGA. The Paralell Filter Architecture for DWT has been improved, calculating wavelet coefficients in real time with hardware reduced to 60%. The new architecture, which also processes IDWT, is implemented with the Radix-2 or the Booth-Wallace Constant multipliers. Including series memory register banks, one integrated circuit Signal Analyzer, ultrasonic range, is presented.

In-process grinding monitoring through acoustic emission

This work aims to investigate the efficiency of digital signal processing tools of acoustic emission signals in order to detect thermal damages in grinding processes. To accomplish such a goal, an experimental work was carried out for 15 runs in a surface grinding machine operating with an aluminum oxide grinding wheel and ABNT 1045 Steel as work material. The acoustic emission signals were acquired from a fixed sensor placed on the workpiece holder. A high sampling rate data acquisition system working at 2.5 MHz was used to collect the raw acoustic emission instead of the root mean square value usually employed. Many statistical analyses have shown to be effective to detect burn, such as the root mean square (RMS), correlation of the AE, constant false alarm rate (CFAR), ratio of power (ROP) and mean-value deviance (MVD). However, the CFAR, ROP, Kurtosis and correlation of the AE have been presented more sensitive than the RMS. Copyright © 2006 by ABCM.

A novel device with 36 channels for imaging and signal acquisition of the gastrointestinal tract based on AC biosusceptometry

The alternate current biosusceptometry (ACB) is a biomagnetic technique used to study some physiological parameters associated with gastrointestinal (GI) tract. For this purpose it applies an AC magnetic field and measures the response originating from magnetic marks or tracers. This paper presents an equipment based on the ACB which uses anisotropic magnetoresistive (AMR) sensors and an inexpensive electronic support. The ACB-AMR developed consists of a square array of 6x6 sensors arranged in a firstorder gradiometer configuration with one reference sensor. The equipment was applied to capture magnetic images of different phantoms and to acquire gastric contraction activity of healthy rats. The results show a reasonable sensitivity and spatial-temporal resolution, so that it may be applied for imaging of phantoms and signal acquisition of the GI tract of small animals. © 2010 IEEE.

Improving synthetic aperture image by image compounding in beamforming process

In this work, signal processing techniques are used to improve the quality of image based on multi-element synthetic aperture techniques. Using several apodization functions to obtain different side lobes distribution, a polarity function and a threshold criterium are used to develop an image compounding technique. The spatial diversity is increased using an additional array, which generates complementary information about the defects, improving the results of the proposed algorithm and producing high resolution and contrast images. The inspection of isotropic plate-like structures using linear arrays and Lamb waves is presented. Experimental results are shown for a 1-mm-thick isotropic aluminum plate with artificial defects using linear arrays formed by 30 piezoelectric elements, with the low dispersion symmetric mode S0 at the frequency of 330 kHz. © 2011 American Institute of Physics.

A brief look at the least-squares approach as a classifier applied to restricted-vocabulary speech recognition

In this letter, a speech recognition algorithm based on the least-squares method is presented. Particularly, the intention is to exemplify how such a traditional numerical technique can be applied to solve a signal processing problem that is usually treated by using more elaborated formulations.

Foetal heart rate recording: analysis and comparison of different methodologies

Monitoring foetal health is a very important task in clinical practice to appropriately plan pregnancy management and delivery. In the third trimester of pregnancy, ultrasound cardiotocography is the most employed diagnostic technique: foetal heart rate and uterine contractions signals are simultaneously recorded and analysed in order to ascertain foetal health. Because ultrasound cardiotocography interpretation still lacks of complete reliability, new parameters and methods of interpretation, or alternative methodologies, are necessary to further support physicians’ decisions. To this aim, in this thesis, foetal phonocardiography and electrocardiography are considered as different techniques. Further, variability of foetal heart rate is thoroughly studied. Frequency components and their modifications can be analysed by applying a time-frequency approach, for a distinct understanding of the spectral components and their change over time related to foetal reactions to internal and external stimuli (such as uterine contractions). Such modifications of the power spectrum can be a sign of autonomic nervous system reactions and therefore represent additional, objective information about foetal reactivity and health. However, some limits of ultrasonic cardiotocography still remain, such as in long-term foetal surveillance, which is often recommendable mainly in risky pregnancies. In these cases, the fully non-invasive acoustic recording, foetal phonocardiography, through maternal abdomen, represents a valuable alternative to the ultrasonic cardiotocography. Unfortunately, the so recorded foetal heart sound signal is heavily loaded by noise, thus the determination of the foetal heart rate raises serious signal processing issues. A new algorithm for foetal heart rate estimation from foetal phonocardiographic recordings is presented in this thesis. Different filtering and enhancement techniques, to enhance the first foetal heart sounds, were applied, so that different signal processing techniques were implemented, evaluated and compared, by identifying the strategy characterized on average by the best results. In particular, phonocardiographic signals were recorded simultaneously to ultrasonic cardiotocographic signals in order to compare the two foetal heart rate series (the one estimated by the developed algorithm and the other provided by cardiotocographic device). The algorithm performances were tested on phonocardiographic signals recorded on pregnant women, showing reliable foetal heart rate signals, very close to the ultrasound cardiotocographic recordings, considered as reference. The algorithm was also tested by using a foetal phonocardiographic recording simulator developed and presented in this research thesis. The target was to provide a software for simulating recordings relative to different foetal conditions and recordings situations and to use it as a test tool for comparing and assessing different foetal heart rate extraction algorithms. Since there are few studies about foetal heart sounds time characteristics and frequency content and the available literature is poor and not rigorous in this area, a data collection pilot study was also conducted with the purpose of specifically characterising both foetal and maternal heart sounds. Finally, in this thesis, the use of foetal phonocardiographic and electrocardiographic methodology and their combination, are presented in order to detect foetal heart rate and other functioning anomalies. The developed methodologies, suitable for longer-term assessment, were able to detect heart beat events correctly, such as first and second heart sounds and QRS waves. The detection of such events provides reliable measures of foetal heart rate, potentially information about measurement of the systolic time intervals and foetus circulatory impedance.

HIGH PERFORMANCE, LOW COST SUBSPACE DECOMPOSITION AND POLYNOMIAL ROOTING FOR REAL TIME DIRECTION OF ARRIVAL ESTIMATION: ANALYSIS AND IMPLEMENTATION

This thesis develops high performance real-time signal processing modules for direction of arrival (DOA) estimation for localization systems. It proposes highly parallel algorithms for performing subspace decomposition and polynomial rooting, which are otherwise traditionally implemented using sequential algorithms. The proposed algorithms address the emerging need for real-time localization for a wide range of applications. As the antenna array size increases, the complexity of signal processing algorithms increases, making it increasingly difficult to satisfy the real-time constraints. This thesis addresses real-time implementation by proposing parallel algorithms, that maintain considerable improvement over traditional algorithms, especially for systems with larger number of antenna array elements. Singular value decomposition (SVD) and polynomial rooting are two computationally complex steps and act as the bottleneck to achieving real-time performance. The proposed algorithms are suitable for implementation on field programmable gated arrays (FPGAs), single instruction multiple data (SIMD) hardware or application specific integrated chips (ASICs), which offer large number of processing elements that can be exploited for parallel processing. The designs proposed in this thesis are modular, easily expandable and easy to implement. Firstly, this thesis proposes a fast converging SVD algorithm. The proposed method reduces the number of iterations it takes to converge to correct singular values, thus achieving closer to real-time performance. A general algorithm and a modular system design are provided making it easy for designers to replicate and extend the design to larger matrix sizes. Moreover, the method is highly parallel, which can be exploited in various hardware platforms mentioned earlier. A fixed point implementation of proposed SVD algorithm is presented. The FPGA design is pipelined to the maximum extent to increase the maximum achievable frequency of operation. The system was developed with the objective of achieving high throughput. Various modern cores available in FPGAs were used to maximize the performance and details of these modules are presented in detail. Finally, a parallel polynomial rooting technique based on Newton’s method applicable exclusively to root-MUSIC polynomials is proposed. Unique characteristics of root-MUSIC polynomial’s complex dynamics were exploited to derive this polynomial rooting method. The technique exhibits parallelism and converges to the desired root within fixed number of iterations, making this suitable for polynomial rooting of large degree polynomials. We believe this is the first time that complex dynamics of root-MUSIC polynomial were analyzed to propose an algorithm. In all, the thesis addresses two major bottlenecks in a direction of arrival estimation system, by providing simple, high throughput, parallel algorithms.

Improving Speech Interaction in Vehicles Using Context-Aware Information through A SCXML Framework

Speech Technologies can provide important benefits for the development of more usable and safe in-vehicle human-machine interactive systems (HMIs). However mainly due robustness issues, the use of spoken interaction can entail important distractions to the driver. In this challenging scenario, while speech technologies are evolving, further research is necessary to explore how they can be complemented with both other modalities (multimodality) and information from the increasing number of available sensors (context-awareness). The perceived quality of speech technologies can significantly be increased by implementing such policies, which simply try to make the best use of all the available resources; and the in vehicle scenario is an excellent test-bed for this kind of initiatives. In this contribution we propose an event-based HMI design framework which combines context modelling and multimodal interaction using a W3C XML language known as SCXML. SCXML provides a general process control mechanism that is being considered by W3C to improve both voice interaction (VoiceXML) and multimodal interaction (MMI). In our approach we try to anticipate and extend these initiatives presenting a flexible SCXML-based approach for the design of a wide range of multimodal context-aware HMI in-vehicle interfaces. The proposed framework for HMI design and specification has been implemented in an automotive OSGi service platform, and it is being used and tested in the Spanish research project MARTA for the development of several in-vehicle interactive applications.