Excitation Source Features Research Articles

Automatic diagnosis of COVID-19 related respiratory diseases from speech.

In this work, an attempt is made to propose an intelligent and automatic system to recognize COVID-19 related illnesses from mere speech samples by using automatic speech processing techniques. We used a standard crowd-sourced dataset which was collected by the University of Cambridge through a web based application and an android/iPhone app. We worked on cough and breath datasets individually, and also with a combination of both the datasets. We trained the datasets on two sets of features, one consisting of only standard audio features such as spectral and prosodic features and one combining excitation source features with standard audio features extracted, and trained our model on shallow classifiers such as ensemble classifiers and SVM classification methods. Our model has shown better performance on both breath and cough datasets, but the best results in each of the cases was obtained through different combinations of features and classifiers. We got our best result when we used only standard audio features, and combined both cough and breath data. In this case, we achieved an accuracy of 84% and an Area Under Curve (AUC) score of 84%. Intelligent systems have already started to make a mark in medical diagnosis, and this type of study can help better the health system by providing much needed assistance to the health workers.

PZT and PVDF piezoelectric transducers’ design implications on their efficiency and energy harvesting potential

Abstract Despite the intensive research carried out in the last two decades, the actual performance of piezoelectric energy harvesters needs significant improvement for widespread applicability. Custom designed experimental set-ups and methods can be applied for the evaluation of new piezoelectric energy harvesters or modified design versions of existing transducers, in terms of efficiency and specific power. In this context, two representative types of commercial cantilever piezoelectric transducers, made of PZT and PVDF material respectively, were tested in various combinations of aerodynamic and harmonic base excitation. A line type laser was used along with long exposure photography for the visualisation of the piezofilm’s mode shapes, tip deflection and the digitization of the elastic line at the oscillation extrema. The harvested power was measured at on-resonance conditions and studied relative to the excitation combinations and the mode shapes. Energy conversion efficiency, defined as the ratio of the electric-field energy accumulated by the supercapacitors, over the total elastic strain energy change of the material during the oscillations is measured and compared. Design improvements are proposed for both transducer types to extract and absorb higher amounts of energy and improve their bandwidth to match the available excitation source characteristics.

Noise spectrum characteristics of marine pump units induced by different excitation sources

To study the noise spectrum characteristics of marine pump units induced by different excitation sources, a computational aeroacoustic (CAA) model of the internal and external field noise of a marine pump was established. The coupled acoustic-vibration method was used to obtain the spectrum characteristics of internal and external field noise. The accuracy and feasibility of the simulation method for noise prediction were confirmed through a noise test. Due to the different mediums in the internal and external fields of the marine pump, an external field acoustic model was established based on the automatically matched layer (AML) technology. The spectral characteristics of different excitation sources and the spatial distribution of the radiated sound field were analyzed, and the contribution of different sound source excitations to the internal and external sound field was revealed. The results show that the main frequency of the internal field noise generated by different excitations is at the blade passing frequency, and the internal field noise induced by the dipole acoustic excitations dominates at 180.6 dB. For the external field noise, the main frequency is still located at the blade passing frequency. The radiation noise induced by the fluid excitation (139.2 dB) is higher than that induced by the dipole excitations (surface dipole, 136.3 dB; rotating dipole, 137.3 dB).

Analysis and classification of speech sounds of children with autism spectrum disorder using acoustic features

Children with autism spectrum disorder (ASD) produce speech sounds different from that of Normal or non-ASD children. Hence, analyzing acoustic features can help characterizing the ASD speech signals. In this study, the distinguishing characteristics of speech production are examined for ASD affected children, with comparison to Normal children’s speech. Acoustic features are analyzed first and then classification of ASD vs Normal speech is attempted using different machine learning techniques. Two speech sound databases are recorded for this study: the speech database of children with ASD and the speech database of Normal children. English speech utterances are recorded for children of Indian regional (Tamil and Telugu) nativity. The changes due to autism effect are examined in context of 5 English vowel sounds (/a/, /e/, /i/, /o/, and /u/). Changes in the speech production characteristics of children are explored using three sets of features. Firstly, changes in the excitation source features are examined using strength of excitation (SoE) and instantaneous fundamental frequency (F0). Secondly, changes in the vocal tract (VT) filter features are examined using dominant frequencies (FD1, FD2) and formant frequencies (F1 to F5). Thirdly, changes in the source-filter combined features are examined using signal energy (E), zero-crossing rate (ZCR), linear prediction cepstrum coefficients (LPCC), and Mel-frequency cepstral coefficients (MFCC). Then, various combinations of the acoustic features are classified utilizing machine learning methods such as probabilistic neural network (PNN), multilayer perceptron (MLP), support vector machine (SVM), and K-nearest neighbors (KNN). Analyses of acoustic features shows significant differences between the speech of children with ASD and the Normal children. Results up to 98.17% accuracy are obtained for classification between acoustic features of the speech sounds of children with ASD and the Normal children. The observations and this study results may be useful as acoustic biomarkers to identify autism and its progression/cure among children. This study may also be valuable towards developing a system for ASD diagnosis from children’s speech sounds, in the future.

Analysis of excitation source characteristics and their contribution in a 2-cylinder diesel engine

Vibration signal of internal combustion engine is excited by the cylinder pressure and other excitations. The response signals caused by different excitations couple together in the time domain and frequency domain, which makes it difficult to extract combustion information from vibration signal. To determine the main excitation sources and the contribution level of the most important excitation that contributes to the vibration in a 2-cylinder diesel engine, the ratios of the maximum value of displacement, velocity and acceleration caused by the non-combustion excitations to those caused by the cylinder pressure are calculated. And a cylinder head-body finite element model of an SD2100TA diesel engine is established to analyze the characteristics of different excitations such as reciprocating inertial force (RIF), piston slap and main bearing load (MBL). According to the analyzed results, the excitations that play a major role on the vibration signal is determined. In addition, the coupling relationship of the excitations is evaluated. The simulation results show that the RIF is the most important excitation in the vibration signal. Finally, the contribution level of the RIF is calculated with the partial coherence function. Results show that the contribution level increases significantly with the increase of the rotation speed and remains basically unchanged with the increase of the torque.

Detection of replay signals using excitation source and shifted CQCC features

The replay attack is refereed as an unauthorized attempt to access the automatic speaker verification (ASV) system by using the pre-recorded speech samples of any target. The replay attack is performed by placing the pre-recorded speech sample of the target before the machine. Of late the replay attack is identified as the greatest threat to ASV system, mainly due to the availability of high quality recording and playback devices. In this work, excitation source feature referred as glottal mel frequency cepstral coefficient (GMFCC) and shifted constant Q cepstral coefficient (SCQCC) are proposed for detection of replay signals. The GMFCC is derived by applying conventional mel-cepstral technique to glottal flow derivative signal. The SCQCC is computed by using constant Q cepstral processing. The effectiveness of the proposed features are demonstrated by conducting experiments with ASVspoof 2017 version 2.0 database. The proposed GMFCC feature provides an equal error rate (EER) of 16.78%, that is 19.63% higher than the recently proposed residual mel frequency cepstral coefficient(RMFCC) feature. The conventional CQCC feature provides an EER of 12.32%. The proposed SCQCC feature provides an EER of 11.34%, shows a relative improvement of 7.94% over CQCC. Further, the CQCC in together with proposed GMFCC provides an EER of 8.82%. On the other hand, the proposed SCQCC+GMFCC system provides an EER of 8.60%. These results signify the usefulness of the proposed system to counter replay attacks.

Robust vowel region detection method for multimode speech

The aim of this paper is to explore a robust method for vowel region detection from multimode speech. In realistic scenario, speech can be classified into three modes namely; conversation, extempore, and read. The existing method detects the vowel form the speech recorded in clean environment which may not be appropriate for the multimode speech tasks. To address this issue, we proposed an approach based on continuous wavelet transform coefficients and phone boundaries for detecting the vowel regions from different modes of the speech signal. For evaluation of the proposed vowel region (VR) detection technique, TIMIT (read speech) and Bengali (read, extempore, and conversation speech) corpora are used. The proposed VR detection technique is compared to the state-of-the-art methods. The experiments has recorded significant gain in the performance of the proposed technique than the state-of-the-art methods. The efficiency of the proposed technique is shown by extracting vocal tract and excitation source features from automatically detected VRs for developing the multilingual speech mode classification (MSMC) model. The evaluation results report that the performance of the MSMC model is significantly improved when features are extracted from the vowel regions than the entire speech utterance.

Estimation of age from speech using excitation source features

Extraction of various distinct features from speech, Gaussian mixture models (GMMs) have been employed as classifiers. Age estimation performance has been inferred by employing excitation source features (LPCCs). The detected age of a speaker is deemed to belong to any of the 9 age groups of 5–10, 10–15, 15–20, 20–25, 25–30, 30–35, 35–40, 40–45 and 45–50. An age group speech corpus has been collected in this work by recording voice of speakers of Hindi language of different age groups and dialects using ten text prompts in neutral speech. Textually neutral Hindi words have been used to construct text prompts which have been recorded in neutral emotion. Different age group has been characterized by using these texts prompt. The average age performance of multispeaker (male + female) is around 94%. In this research, classification of different group of speakers has been done on the basis of excitation source in human speech.

DNN-HMM-Based Speaker-Adaptive Emotion Recognition Using MFCC and Epoch-Based Features

Speech is produced when time varying vocal tract system is excited with time varying excitation source. Therefore, the information present in a speech such as message, emotion, language, speaker is due to the combined effect of both excitation source and vocal tract system. However, there is very less utilization of excitation source features to recognize emotion. In our earlier work, we have proposed a novel method to extract glottal closure instants (GCIs) known as epochs. In this paper, we have explored epoch features namely instantaneous pitch, phase and strength of epochs for discriminating emotions. We have combined the excitation source features and the well known Male-frequency cepstral coefficient (MFCC) features to develop an emotion recognition system with improved performance. DNN-HMM speaker adaptive models have been developed using MFCC, epoch and combined features. IEMOCAP emotional database has been used to evaluate the models. The average accuracy for emotion recognition system when using MFCC and epoch features separately is 59.25% and 54.52% respectively. The recognition performance improves to 64.2% when MFCC and epoch features are combined.

Stability analysis of floating raft system under multiexcitation condition

A floating raft system is subjected to multiple excitation sources with multiple frequencies for each excitation source. Considering the two characteristics of excitation source, the stability of floating raft system was analyzed. A vibration equation for the floating raft system under multiexcitation condition was established. A multiscale method was then used to solve the equation. The amplitude–frequency response equation and unstable region of solution are discussed. The results show that the vibration of raft frame fits the pattern of soft-spring vibration. This indicates that the excitation of main raft unit with a rigid connection compromises the stability of the system, whereas the excitation of unit with elastic connection increases stability.

Multilingual and multimode phone recognition system for Indian languages

The aim of this paper is to develop a flexible framework capable of automatically recognizing phonetic units present in a speech utterance of any language spoken in any mode. In this study, we considered two modes of speech: conversation and read modes in four Indian languages, namely, Telugu, Kannada, Odia, and Bengali. The proposed approach consists of two stages: (i) Automatic speech mode classification (SMC) and (ii) Automatic phoneme recognition using mode-specific multilingual phone recognition system (MMPRS). The vocal tract and excitation source features are considered for classifying speech modes using feed forward neural networks (FFNNs). The vocal tract, excitation source, and tandem features are used in training deep neural network (DNN)-based multilingual phone recognition systems (MPRSs). The performance of the proposed approach is compared with baseline mode-dependent and mode-independent MPRSs. Experimental results show that the proposed approach which combines both SMC and MMPRS into a single system outperforms the baseline phone recognition systems.

Exploration of excitation source information for shouted and normal speech classification.

Discrimination between shouted and normal speech is an essential prerequisite for many speech processing applications. Existing works have established that excitation source information plays a significant role in shouted speech production. In speech processing literature, various features have been proposed to model different aspects of the excitation source. The principal contribution of this work is to explore three such features, Discrete Cosine Transform of Integrated Linear Prediction Residual (DCT-ILPR), Mel-Power Difference of Spectrum in Sub-bands (MPDSS), and Residual Mel-Frequency Cepstral Coefficient (RMFCC), for shouted and normal speech classification. The DCT-ILPR feature represents the shape of the glottal cycle, MPDSS estimates the periodicity of the excitation source spectrum, and RMFCC characterizes smoothed spectral information of the excitation source. The authors have also contributed a dataset containing shouted and normal speech. This work is evaluated on three datasets and benchmarked against three baseline methods. Deep neural networks are used to study the classification performance of individual features and their combinations. The generalization performance of features (and combinations) is also investigated. Fusion of excitation source features with Mel-Frequency Cepstral Coefficients (MFCC) provides the best performance compared to other combinations. Noise analysis shows that adding excitation features with MFCC+ΔΔ provides a more robust classification system.

Automatic Evaluation of Song Intelligibility Using Singing Adapted STOI and Vocal-Specific Features

An objective machine-driven measure of song intelligibility would be of great utility for various music information retrieval tasks. Song intelligibility mostly depends on two factors, the amount of interference caused by background accompaniment, and the quality of singing vocal. We leverage these two factors to determine the intelligibility of a song. For the first factor, we adapt a well known method for intelligibility prediction of noisy speech, short term objective intelligibility (STOI), to singing. The singing-adapted STOI considers the polyphonic song as a time-frequency weighted noisy version of the extracted singing vocal. We use U-net based audio source separation method to extract singing vocal from a polyphonic song. The singing vocal shares the same underlying physiological mechanism for production as that of speech, with some differences in the pronunciation and prosody of the phonemes. Therefore, for the second factor, we have introduced vocal-specific features to measure the intelligibility of the singing vocal, which are excitation source, spectral, and prosodic singing characteristics. We perform detailed analysis on each of these features to establish their efficacy for quantifying song intelligibility. We train a regression model to derive the intelligibility scores using a combination of the vocal-specific features and singing adapted STOI, obtaining a significant improvement in performance. The correlation between the intelligibility score obtained using proposed framework and human-rated intelligibility score is 0.81, which shows the efficacy of the proposed approach.

Analysis of aperiodicity in artistic Noh singing voice using an impulse sequence representation of excitation source.

Aperiodicity in the voice source is caused by changes in the vocal fold vibrations, other than the normal quasi-periodicity and the turbulence at the glottis. The aperiodicity appears to be one of the main properties that is responsible for conveying the emotion in artistic voices. In this paper, the feasibility of representing the excitation source characteristics in artistic (Noh) singing voice by an impulse-like sequence in the time domain is examined. The impulses at the glottal closure instants contribute to the major excitation of the vocal tract system. The sequence of such impulses produces harmonics of the fundamental frequency in the spectrum. The amplitude variation or amplitude modulation (AM) of these impulses in the sequence contributes to the aperiodicity in the excitation, and can result in appearance of subharmonics in the spectrum. The variation in the impulse intervals or frequency modulation (FM) can also contribute to the aperiodicity in the excitation. The aperiodic component of the excitation in the Noh voice is examined in the impulse-like sequence derived from the signal using the single frequency filtering analysis. The effects of aperiodicity are explained for synthetic AM and FM sequences of impulses using spectrograms and saliency plots.

Quantum Confinement Explains Pump-Dependent Luminescence from Butyl-Terminated Si Quantum Dots

The origin of the luminescence of colloidal organically terminated silicon quantum dots is the topic of prime importance both from a fundamental point of view and in terms of various applications. In order to shed light on this topic, one should find out whether the basic principles of a particular theoretical approach are coherent with the experimental spectra and characteristics of real specimens with their inevitable imperfections. In this work, we develop a phenomenological semi-analytical method that matches (i) photoluminescence (PL) spectra of silicon colloidal quantum dots, (ii) size distribution of quantum dots, and (iii) excitation source characteristics. The method is based on the (i) log-normal size distribution of quantum dots, (ii) shifted log-normal distribution of optically excited dots, and (iii) influence of quantum confinement on emission and absorption. The formalism has been applied for the analysis of experimental PL spectra of butyl-terminated silicon quantum dots (reported in Dohna...

Usefulness of linear prediction residual for replay attack detection

This work demonstrates the usefulness of processing linear prediction (LP) residual signal for detecting replay attacks. The playback device having non-flat frequency response modulates the input signal passing through it, resulting spectral distortion in replay signals especially in the low frequency regions (0–300 Hz). In effect, the excitation source information present below 300 Hz gets distorted. The linear prediction (LP) residual signal implicitly contains excitation source information. The excitation source feature, residual mel frequency cepstral coefficients (RMFCC) obtained from the LP residual signal has been proposed for replay detection task. The significance of RMFCC feature has been investigated through Gaussian mixtures model-universal background model (GMM-UBM) ASV experiments and spoof detection experiments using self-developed IITG-MV replay database and standard ASVspoof 2017 database, respectively. For IITG-MV, relative tandem-detection cost function (t-DCF) improvements of 29.78% (male), 7.96% (female) and 24.52% (whole-set) are observed for RMFCC+MFCC combination over MFCC feature. For ASVspoof 2017, relative EER improvements of 37.34% are reported for RMFCC+CQCC combination over CQCC feature. Minimum reported EER is 9.50% for RMFCC+CQCC system. Experimental results shows that the RMFCC feature contains information complementary to MFCC and CQCC features.

Detection of Nasalized Voiced Stops in Cleft Palate Speech Using Epoch-Synchronous Features

The presence of velopharyngeal dysfunction in individuals with cleft palate CP nasalizes the voiced stops. Due to this, voiced stops /b/, /d/, /g/ tend to be perceive like nasal consonants /m/, /n/, /ng/. In this work, a novel algorithm is proposed for the detection of nasalized voiced stops in CP speech using epoch-synchronous features. Speech regions corresponding to consonant and consonant-vowel transitions are segmented using the knowledge of glottal activity, syllable nucleus, low-frequency spectral dominance, and vowel onset point. The segmented regions are epoch-synchronously processed to analyze the spectral, spectro-temporal, excitation source, and periodicity characteristics of normal and nasalized voiced stops. Spectral and spectro temporal features are computed using single pole filter based time-frequency representation. The amplitude of Hilbert envelope of linear prediction residual, measured around the epoch is used to analyze the effect of nasalization on excitation source. Comparison of speech frames of successive inter-epoch intervals is carried out to analyze the periodicity characteristics. The proposed features are used to develop a support vector machine classifier for the classification of normal and nasalized voiced stops. Segmentation accuracy for the proposed knowledge based method is found to be better than the hidden Markov model based force-alignment approach. The detection rate of nasalized voiced stops is found to be high for the proposed epoch synchronous features than the conventional Mel-frequency cepstral coefficients.

On a space-time regularization for force reconstruction problems

Abstract Tikhonov and LASSO regularizations are commonly used to solve force reconstruction problems in time domain. Unfortunately, these particular forms of additive regularization are not well adapted to tackle both localization and time reconstruction problems simultaneously, since they are generally restricted to the reconstruction of sources sharing the same space and time characteristics. To alleviate this limitation, a multiplicative space-time regularization is introduced. The proposed regularization strategy takes advantage of one’s prior knowledge of the space-time characteristics of excitation sources. It also introduces a novel reconstruction model based on the generalized- α method, which is unconditionally stable and second-order accurate. The validity of the proposed method is assessed numerically and experimentally. In particular, comparisons with standard regularization terms point out the practical benefit in exploiting both spatial and temporal prior information simultaneously in terms of quality and robustness of reconstructed solutions.

Exploring Text-Constraint Models and Source Information for Long-Enrollment with Short-Test Speaker Verification

This work focuses on long-enrollment with short-test speaker verification (SV) from the perspective of application-oriented systems. The importance of phonetic match between train and test models is explored in terms of having a text-constraint model-based framework on Part IV of RedDots database. This database has a text-dependent and a text-prompted-based enrollment conditions for speaker modeling. Two different text-constraint setups are formalized for evaluating the effect of text match on train and test sessions. Further, the excitation source features mel power difference of spectrum in subbands, residual mel frequency cepstral coefficient and discrete cosine transform of integrated linear prediction residual are investigated to determine their significance for text-constraint-based framework. Although the source features individually perform poorer compared to the conventional mel frequency cepstral coefficient (MFCC) features, their significance is reflected in fusion due to the complementary nature of information carried by them. Additionally, the source features become imperative for text-constraint-based models for long-enrollment with short-test SV in fusion to MFCC features and achieves commendable improvement from baseline framework of text-prompted-based enrollment condition. This thus minimizes the performance difference between text-dependent and text-prompted-based enrollment condition showing importance of text-constraint models and source information in long-enrollment with short-test-based framework favorable from the perspective of field deployable systems.

I-Vector-Based Speaker Verification on Limited Data Using Fusion Techniques

Abstract In many biometric applications, limited data speaker verification plays a significant role in practical-oriented systems to verify the speaker. The performance of the speaker verification system needs to be improved by applying suitable techniques to limited data condition. The limited data represent both train and test data duration in terms of few seconds. This article shows the importance of the speaker verification system under limited data condition using feature- and score-level fusion techniques. The baseline speaker verification system uses vocal tract features like mel-frequency cepstral coefficients, linear predictive cepstral coefficients and excitation source features like linear prediction residual and linear prediction residual phase as features along with i-vector modeling techniques using the NIST 2003 data set. In feature-level fusion, the vocal tract features are fused with excitation source features. As a result, on average, equal error rate (EER) is approximately equal to 4% compared to individual feature performance. Further in this work, two different types of score-level fusion are demonstrated. In the first case, fusing the scores of vocal tract features and excitation source features at score-level-maintaining modeling technique remains the same, which provides an average reduction approximately equal to 2% EER compared to feature-level fusion performance. In the second case, scores of the different modeling techniques are combined, which has resulted in EER reduction approximately equal to 4.5% compared with score-level fusion of different features.