Department Publications

This paper presents an effective method of identifying elephant rumbles in infrasonic seismic signals. The design and implementation of electronic circuitry to amplify, filter, and digitize the seismic signals captured through geophones are presented. A collection of seismic infrasonic elephant rumbles was collected at a free-ranging area of an elephant orphanage in Sri Lanka. The seismic rumbles were converted to spectrograms, and several methods were used for spectral feature extraction. Using LasyPredict, the features extracted using different methods were fed into their corresponding machine-learning algorithms to train them for automatic seismic rumble identification. It was found that the Mel frequency cepstral coefficient (MFCC) together with the Ridge classifier machine learning algorithm produced the best performance in identifying seismic elephant rumbles. A novel method for denoising the spectrum that leads to enhanced accuracy in identifying seismic rumbles is also presented.

Hearing-impaired listeners have a reduced ability to selectively attend to sounds of interest amid distracting sounds in everyday environments. This ability is not fully regained with modern hearing technology. A better understanding of the brain mechanisms underlying selective attention during speech processing may lead to brain-controlled hearing aids with improved detection and amplification of the attended speech. Prior work has shown that brain responses to speech, measured with magnetoencephalography (MEG) or electroencephalography (EEG), are modulated by selective attention. These responses can be predicted from the speech signal through linear filters called Temporal Response Functions (TRFs). Unfortunately, these sensor-level predictions are often noisy and do not provide much insight into specific brain source locations. Therefore, a novel method called Neuro-Current Response Functions …

In this paper, we consider the problem of recovering speech from audio recordings of on-board microphones in a noisy drone platform. Enhancement of speech degraded by drone noise is considered to be a difficult task due to the strong noise generated from its motors and propellers causing an extremely low signal-to-drone noise ratio (SdNR). We propose a solution by (i) developing a multichannel Wiener filter (MWF) to remove drone noise from microphone recordings, and (ii) further reduction of residual noise using a Gaussian mixture model (GMM) based dual-stage parametric Wiener filter (WF). The method exploits the known statistics of motor current-specific drone noise. The theory developed is applicable to irregular microphone array embedded in a drone enabling realistic integration to most drones. We evaluate the proposed framework using two different drone acoustics datasets under extreme SdNR levels including− 30 dB. The experimental results confirm promising performance in terms of SdNR improvement, speech quality (PESQ), and intelligibility (STOI) and show a strong potential for speech enhancement applications using noisy drones.

In this paper, we consider the problem of recovering desired sound source signals from on-board microphone recordings on a noisy drone.  Enhancement of source signal degraded by drone noise is considered to be a difficult task due to the strong noise generated from its motors and propellers causing an extremely low signal-to-drone noise ratio (SDNR).  We propose a solution (i) by using a multichannel Wiener filter (MWF) to remove drone noise from microphone recordings, and (ii) further reduction of residual noise using a Gaussian mixture model (GMM) based dual-stage parametric Wiener filter (WF).  The method exploits known statistics of motor current-specific drone noise.  The theory developed is applicable to irregular microphone arrays embedded on a drone enabling realistic integration to most drones. We demonstrate the validity of the proposed framework through (i) experimental recordings from two …

This paper presents a sound source localization method using an irregular microphone array embedded in a drone. Sound source localization is an integral function of drone audition systems which enables various applications of drones such as search and rescue missions. However, the audio recordings using the on-board microphones obscure the sound emitted by a source on the ground due to drone generated motor and propeller noise, thus leading to an extremely low signal-to-drone noise ratio (SdNR). In this paper, we propose a cross-correlation based direction of arrival (DOA) estimation technique using the time difference of arrival (TDOA) at different microphone pairs, with noise angular spectrum subtraction. Through the measured current-specific drone noise spectrum, noise suppression has been achieved from the multi-channel recordings. Experimental results show that the proposed method is capable …

Objective The Temporal Response Function (TRF) is a linear model of neural activity time-locked to continuous stimuli, including continuous speech. TRFs based on speech envelopes typically have distinct components that have provided remarkable insights into the cortical processing of speech. However, current methods may lead to less than reliable estimates of single-subject TRF components. Here, we compare two established methods, in TRF component estimation, and also propose novel algorithms that utilize prior knowledge of these components, bypassing the full TRF estimation. Methods We compared two established algorithms, ridge and boosting, and two novel algorithms based on Subspace Pursuit (SP) and Expectation Maximization (EM), which directly estimate TRF components given plausible assumptions regarding component characteristics. Single-channel, multi-channel, and source-localized …

This paper proposes a single-channel speech enhancement method to reduce the noise and enhance speech at low signal-to-noise ratio (SNR) levels and non-stationary noise conditions. Specifically, we focus on modeling the noise using a Gaussian mixture model (GMM) based on a multi-stage process with a parametric Wiener filter. The proposed noise model estimates a more accurate noise power spectral density (PSD), and allows for better generalization under different noise conditions such as harmonic and babble noise environments compared to traditional Wiener filtering methods. Simulations show that the proposed approach can achieve better performance in terms of speech quality (PESQ) and intelligibility (STOI) at low SNR levels.

Primary auditory cortex is a critical stage in the human auditory pathway, a gateway between subcortical and higher-level cortical areas. Receiving the output of all subcortical processing, it sends its output on to higher-level cortex. Non-invasive physiological recordings of primary auditory cortex using electroencephalography (EEG) and magnetoencephalography (MEG), however, may not have sufficient specificity to separate responses generated in primary auditory cortex from those generated in underlying subcortical areas or neighboring cortical areas. This limitation is important for investigations of effects of top-down processing (e.g., selective-attention-based) on primary auditory cortex: higher-level areas are known to be strongly influenced by top-down processes, but subcortical areas are often assumed to perform strictly bottom-up processing. Fortunately, recent advances have made it easier to isolate the neural activity of primary auditory cortex from other areas. In this perspective, we focus on time-locked responses to stimulus features in the high gamma band (70–150 Hz) and with early cortical latency (∼40 ms), intermediate between subcortical and higher-level areas. We review recent findings from physiological studies employing either repeated simple sounds or continuous speech, obtaining either a frequency following response (FFR) or temporal response function (TRF). The potential roles of top-down processing are underscored, and comparisons with invasive intracranial EEG (iEEG) and animal model recordings are made. We argue that MEG studies employing continuous speech stimuli may offer particular benefits, in that …

Cortical processing of arithmetic and of language rely on both shared and task-specific neural mechanisms, which should also be dissociable from the particular sensory modality used to probe them. Here, spoken arithmetical and non-mathematical statements were employed to investigate neural processing of arithmetic, compared with general language processing, in an attention-modulated cocktail party paradigm. Magnetoencephalography (MEG) data were recorded from 22 human subjects listening to audio mixtures of spoken sentences and arithmetic equations while selectively attending to one of the two speech streams. Short sentences and simple equations were presented diotically at fixed and distinct word/symbol and sentence/equation rates. Critically, this allowed neural responses to acoustics, words, and symbols to be dissociated from responses to sentences and equations. Indeed, the simultaneous …

Cortical processing of arithmetic and of language rely on both shared and task-specific neural mechanisms, which should also be dissociable from the particular sensory modality used to probe them. Here, spoken arithmetical and non-mathematical statements were employed to investigate neural processing of arithmetic, compared to general language processing, in an attention-modulated cocktail party paradigm. Magnetoencephalography (MEG) data were recorded from 22 human subjects listening to audio mixtures of spoken sentences and arithmetic equations while selectively attending to one of the two speech streams. Short sentences and simple equations were presented diotically at fixed and distinct word/symbol and sentence/equation rates. Critically, this allowed neural responses to acoustics, words, and symbols to be dissociated from responses to sentences and equations. Indeed, the simultaneous neural processing of the acoustics of words and symbols were observed in auditory cortex for both streams. Neural responses to sentences and equations, however, were predominantly to the attended stream, originating primarily from left temporal, and parietal areas, respectively. Additionally, these neural responses were correlated with behavioral performance in a deviant detection task. Source-localized Temporal Response Functions revealed distinct cortical dynamics of responses to sentences in left temporal areas and equations in bilateral temporal, parietal, and motor areas. Finally, the target of attention could be decoded from MEG responses, especially in left superior parietal areas. In short, the neural responses to arithmetic …

Our ability to communicate using speech depends on complex, rapid processing mechanisms in the human brain. These cortical processes make it possible for us to easily understand one another even in noisy environments. Measurements of neural activity have found that cortical responses time-lock to the acoustic and linguistic features of speech. Investigating the neural mechanisms that underlie this ability could lead to a better understanding of human cognition, language comprehension, and hearing and speech impairments.

Neural processing along the ascending auditory pathway is often associated with a progressive reduction in characteristic processing rates. For instance, the well-known frequency-following response (FFR) of the auditory midbrain, as measured with electroencephalography (EEG), is dominated by frequencies from ∼100 Hz to several hundred Hz, phase-locking to the acoustic stimulus at those frequencies. In contrast, cortical responses, whether measured by EEG or magnetoencephalography (MEG), are typically characterized by frequencies of a few Hz to a few tens of Hz, time-locking to acoustic envelope features. In this study we investigated a crossover case, cortically generated responses time-locked to continuous speech features at FFR-like rates. Using MEG, we analyzed responses in the high gamma range of 70–200 Hz to continuous speech using neural source-localized reverse correlation and the …

The potential of drone based services is enormous with applications ranging from consumer product delivery to health services. When meeting this demand, one of the major challenges we face is the noise produced by drones, which not only contributes to listener discomfort, but also hinders the device's ability to effectively communicate via audio. Thus, there exists a pressing need for understanding the characteristics of drone related noise, which can then be suppressed using suitable methods. This paper presents a preliminary study on modeling the relationship between input motor current and acoustic noise produced by a drone. An experimental study is conducted indoors for a drone under hovering manoeuvre with a single active motor and propeller. The drone noise was measured by a single on-board microphone. We identify multiple tones or harmonics in the drone noise spectrum that vary proportionally …

This paper presents the development of a Sinhala Speech Recognition System to be deployed in an Interactive Voice Response (IVR) system of a telecommunication service provider. The main objectives are to recognize Sinhala digits and names of Sinhala songs to be set up as ringback tones. Sinhala being a phonetic language, its features are studied to develop a list of 47 phonemes. A continuous speech recognition system is developed based on Hidden Markov Model (HMM). The acoustic model is trained using the voice through mobile phone. The outcome is a speaker independent speech recognition system which is capable of recognizing 10 digits and 50 Sinhala songs. A word error rate (WER) of 11.2% using a speech corpus of 0.862 hours and a sentence error rate (SER) of 5.7% using a speech corpus of 1.388 hours are achieved for digits and songs respectively.

Voice Controlled Robot (VCR) is a mobile robot whose motions can be controlled by the user by giving specific voice commands. The speech recognition software running on a PC is capable of identifying the 5 voice commands ‘Run’,‘Stop’,‘Left’,’Right’and ‘Back’issued by a particular user. After processing the speech, the necessary motion instructions are given to the mobile platform via a RF link. Following is the system overview. The speech recognition software is speaker dependant. The special feature of the application is the ability of the software to train itself for the above voice commands for a particular user. The graphical user interface running along with the software provides a very convenient method for the users to train. It also provides many other facilities in operating the robot.

It is a vital requirement to have passive noise control enclosure in order to depress air borne noise of reciprocating engine type power generators. The design of these enclosures needs to be optimized in terms of the sound pressure level and the designing cost. We have used the existing acoustic equations to obtain the optimization based on the objective functions derived for the sound pressure level and enclosure design cost. Metaheuristic optimization algorithms such as genetic algorithms and particle swarm algorithm are capable of solving these optimization problems which have constraints for different parameters. The results obtained for a real world design problem confirms that particle swarm optimization provides better results than genetic algorithm in terms of optimality of the solutions and also the computational efficiency. Furthermore, it was observed that there is a significant linear relationship (R …

Voice commands have been used as the basic method of interaction between humans and robots over the years. Voice interaction is natural and require no additional technical knowledge. But while using voice commands humans frequently use uncertain information. In the case of object manipulation on a table, frequently used uncertain terms “Left,“Right”,“Middle”,“Front”... etc. These terms fail to depict an exact location on the table and the interpretation is governed by the robots point of view. Depending solely on vocal cues is not ideal as it requires the users to explain the exact location with more words and phrases making the interaction process cumbersome and less human like. However, using hand gestures to pinpoint the location is as natural as using the voice commands and frequently used when manipulating items on a surface. When compared to voice commands use of hand gestures is a more direct and less cumbersome approach. But when used alone hand gestures can result in errors while extracting the pointed location making the user dissatisfied. This paper proposes a multi-modal interaction method which uses hand gestures combined with voice commands to interpret uncertain information when placing an object on a table. Two fuzzy inference systems have been used to interpret the uncertain terms related to the two axes of the table. The proposed system has been implemented on an assistive robot platform. Experiments have been conducted to analyze the behaviour of the system.

Visible Light Communication (VLC) is emerging as a next generation data transmission method for short-range communication applications. In this paper we implement and characterize two prototype stereo audio streaming methods utilizing VLC. A software architecture is developed to process and stream data. The software architecture is bridged with a hardware section, which facilitates free-space VLC channel, over a Universal Serial Bus (USB) to serial interface. A particularly attractive feature of our system is that it uses commonly available, low-cost components which enables its implementation in everyday applications.

Real-time scanned-array direct-form-I hardware implementations of two-dimensional (2D) infinite impulse response (IIR) frequency-planar beam plane-wave (PW) filters have potentially wide applications in the directional enhancement of spatio-temporal broadband PWs based on their directions of arrival (DOAs). The proposed prototypes consist of a microphone sensor array, low-noise-amplifiers (LNAs), multiplexers (MUXs), a programmable gain amplifier (PGA), an analog to digital converter (ADC), a digital to analog converter (DAC), and a field programmable gate array (FPGA) circuit based 2D IIR spatio-temporal beam filter implemented on a single Xilinx Virtex2P xc2vp30-7ff896 FPGA chip. Starting from published 1 st -order designs, novel FPGA architectures for highly-selective 2 nd - and 3 rd -order beam PW filters are proposed, simulated, implemented on FPGA, and verified on-chip.

Beamforming, in brief, is a signal processing technique which has potential applications in the areas such as sonar, ultrasound, seismic, microwave imaging, radio astronomy and communications. In this report we are presenting a prototype that filters audio signals of interest, based on their direction of arrival (DOA). The prototype described in this report consists of both hardware and software. A microphone sensor array, low-noise-amplifiers, multiplexer, adjustable gain controller, FPGA development board and speakers constitute the hardware. FPGA processor is embedded with a 2D IIR beam filter. The hardware take the audio inputs, multiplex them, digitize them and finally fed them in to FPGA processor. The digital filter, filters the asynchronously sampled broadband spatio-temporal plane-wave signals based on DOA and yields a processed signal as the output. Further the report describes the synthesis of 2D IIR …

Sonar sensors are widely used in obstacle detection in mobile robotic applications and certain limitations of these sensors usually become the reason for failures in these applications. Therefore, a thorough analysis of the actual behavior of sonar sensors is required. This research studied Devantech SRF05 sonar sensor, which is the most common sonar sensor in practice. We have discovered its practical beam pattern in 3-dimension (3D), optimum trigger frequency, and maximum angle of detection.

This paper describes a baby sitting robot system, which has the capabilities of baby tracking , cry signal processing, map building and obstacle avoidance, path planning, entertain the baby or alarm the guardian if any defined anomalies found and voice interaction. For that purpose, the baby sitting robot system has a capability to track and follow the baby with obstacle avoidance. It is also potential enough to identify when the baby cries, or reach near to any defined anomalies. Further more it provides a convenient voice interface for easy usage and various entertainment services for the baby. Rather than just notify the parents that the baby is approaching anomalies, it will try to prevent it from reaching the anomalies by either blocking or distracting with music. In this paper, the overall system is introduced and the detailed subsystems and functions are presented. Baby tracking, cry detection and step detection have …

The performance of nonlinear adaptive filters in modeling devices with mild and moderately strong nonlinearities such as hearing aids was investigated. The existence on nonlinearities in hearing aids and that nonlinear adaptive filters were better suited for hearing aid modeling compared to their linear counterparts with equal number of filter coefficients. The signal to noise ratio improvement in modeling showed improvements in the range of 5% to 50%. The results suggested that as the nonlinearity of the device becomes stronger, a larger number of nonlinear coefficients should be used.

The paper describes several digital signal processing (DSP) techniques used in the development of a computer-based speech trainer for hearing impaired children. Children with congenital hearing impairments have difficulties in speaking, and even in making the basic sounds associated with speech. Speech therapists use specialized training methods to train such children. The dearth of qualified speech therapists, and other facilities hinder the speech development of many children in need of such training in Sri Lanka. The speech trainer described in this paper was developed as an alleviation to the above problem. The training tool developed, will aid a child with initial guidance from an adult, to master the pronunciation of initial sounds taught in a speech therapy programme, in a game-like environment. In its current status, the training tool can guide children in pronouncing the five vowel sounds, the first step in …

The paper describes the development of a speech trainer based on digital signal processing (DSP) techniques, for hearing impaired children. The DSP techniques investigated in the implementation of this software-based speech trainer, the final" product'and its degree of success in actual use are highlighted. Children with congenital hearing impairments have difficulties in speaking, and even in making the basic sounds associated with speech. Speech therapists use specialized training methods to train such children. The first step in such programs is the training of the pronunciation of common sounds. The dearth of qualified speech therapists, and other facilities hinder the speech development of many children in need of such training.