Spectral Centroid Research Articles

Assessment of wood quality for Sape making: Vibroacoustic analysis and machine learning classification

Sape is a popular traditional musical instrument from Sarawak, Malaysia. This instrument is handmade and differs in wood, dimension, design, etc. This impedes the preservation and promotion of the Sape tradition, as well as the development of new Sape instruments. Wood is the primary factor affecting Sape sound, and this study aimed to evaluate the quality of three commonly used types of wood in the instrument manufacturing. Rectangular wood samples were fashioned and tested for physical, vibroacoustic, and timbre characteristics using a flexural vibration test. The objective was to identify the top features influencing the sound quality and develop a reliable method for classifying wood quality. Results showed that Adau wood had the highest quality, followed by Merbau and Tapang wood. Four key features, including acoustic radiation damping coefficient, spectral flux, spectral centroid, and inharmonicity, were selected by the MRMR algorithm and used to train and test various classifiers in MATLAB. The decision tree classifier achieved 98.1% accuracy in predicting wood quality. This study demonstrates the potential of using machine learning to classify Sape wood quality and provides a useful guide for its production. The findings could contribute to the preservation and advancement of this cultural tradition.

Best descriptors for predicting noise annoyance and spectrum-based penalty of steady-state wideband noise

Many objective descriptors (i.e., single-number quantities) are available in the literature for the objective assessment of noise annoyance of wideband, steady-state sounds. However, there is no definitive understanding of which descriptors best correspond to subjective annoyance. Our purpose is to assess how different descriptors correspond with differences in noise annoyance resulting from changes in A-weighted sound level and spectrum. This investigation is based on recently published results from a psychoacoustic experiment conducted by Kuusinen et al. [1]. They investigated 23 steady-state wideband noises with various spectral shapes within 32-48 dB LAeq, and participants rated them in terms of subjective annoyance. The study revealed that penalty due to spectrum shape could be even 10 dB. Here, we present a follow up analysis focusing on objective noise descriptors. The results indicate that many descriptors are strongly associated with noise annoyance ratings, while Spectral Centroid and Sharpness appear to be the best candidates to predict spectrum-based penalty.

Studying environment sounds using transfer entropy: Application to an urban park in the city of Milan, Italy

Sounds in large cities are usually characterized by multi-source overlaying components. This makes environment sound quality difficult to interpret, thus requiring different investigation approaches. This is the case of urban parks where the coexistence of anthropogenic and biophonic sound sources makes the evaluation of the local soundscape quality challenging. In this context, we applied the transfer entropy measure to extract additional information with respect to the more classical approach of eco-acoustics. The case study refers to the Parco Nord of Milan, Italy, for which classical soundscape analysis is already available. We used sound recordings (3.5h long each) taken over an area of approximately 20 hectares using 16 sensors. We calculated the classical eco-acoustic indices and studied the transfer entropy among all sites. The considered time series corresponded to three representative eco-acoustic indices (Acoustic Diversity Index, ADI, Acoustic Complexity Index, ACI and Dynamic Spectral Centroid, DSC calculated for all the 16 sites with 1-minute time resolution) obtained after a principal components analysis. A preliminary interpretation of the results is provided by selecting a representative index from one principal component and by comparing its behavior with a previous standard soundscape analysis performed by the authors for the same index and area.

Gender and age biases in the assessment of speech accuracy: A study of speech-language clinicians' ratings of /s/ accuracy.

Typically developing children assigned male at birth (AMAB) and children assigned female at birth (AFAB) produce the fricative /s/ differently: AFAB children produce /s/ with a higher spectral peak frequency. This study examined whether implicit knowledge of these differences affects speech-language pathologists'/speech and language therapists' (SLPs'/SLTs') ratings of /s/ accuracy, by comparing ratings made in conditions where SLPs/SLTs were blind to children's sex assigned at birth (SAB) to conditions in which they were told this information. SLPs (n = 95) varying in clinical experience rated the accuracy of word-initial /s/ productions (n = 87) of eight children with speech sound disorder in one of four conditions: one in which no information about the children was revealed, one in which children's SAB was revealed, one in which children's age was revealed, and one in which both were revealed. Despite there being no statistically significant differences between AFAB and AMAB children's /s/ production in researcher-determined accuracy or in one acoustic characteristic, spectral centroid, SLPs in all four conditions judged the /s/ productions of AFAB children as more accurate than AMAB children. Listeners were significantly less likely to judge the productions of AMAB children to be inaccurate in the conditions in which age or age and SAB were revealed. These effects were consistent across SLPs with greatly varying levels of clinical experience. Knowing or imputing children's age and SAB can affect ratings of /s/ accuracy. Clinicians should be mindful of these potential effects. Future research should understand how expectations about sociolinguistic variation in speech affect appraisals of their speech and language. What is already known on the subject Adult men and women produce /s/ differently. A consensus is that these differences reflect sociolinguistic gender marking, rather than being the passive consequence of vocal-tract differences. Recent studies have shown that children assigned female at birth (AFAB) and those assigned male at birth (AMAB) produce /s/ differently in ways that mirror the differences between adult men and women, and which presumably reflect gender marking. What this paper adds to existing knowledge We asked whether US-based speech-language pathologists' (SLPs) ratings of the accuracy of /s/ differ depending on whether they are rating an AFAB or an AMAB child, and whether these differences are greater in conditions in which people are told the sex assigned at birth of the child being rated. We found that SLPs were more likely to judge AFAB children's /s/ productions to be more accurate than AMAB children's, even though the productions from the AMAB and AFAB children that were used as stimuli were matched for accuracy as determined by trained researchers. What are the clinical implications of this work? SLPs/speech-language therapists should be sensitive to the influence of social variables when assessing /s/. SLPs/speech-language therapists might rate children's productions differently depending on whether they believe they are rating an AFAB or an AMAB child.

Automated Classification of Egg Freshness Using Acoustic Signals and Convolutional Neural Networks

Abstract The acoustic response of eggs has not been fully optimized for quality detection purposes. This research investigates the utilization of acoustic response as input features for classifying fresh and rotten eggs using Convolutional Neural Networks (CNN). Acoustic measurements were conducted using an experimental setup involving a striking rod, microphone, and microcontroller to capture acoustic responses from eggs struck vertically and horizontally. Features such as energy, entropy, zero crossing rate, spectral centroid, and Mel Frequency Cepstral Coefficients (MFCC) were extracted from the recorded acoustic signals. The study utilized a sample set of 200 intact chicken eggs without cracks, equally split between fresh and rotten eggs. Principal Component Analysis (PCA) revealed significant differences in acoustic responses between fresh and rotten eggs, with clear separation observed in horizontal measurements. Three primary classification models—Convolutional Neural Network (CNN), Deep Neural Network (DNN), and Support Vector Machines (SVM)—were evaluated for this classification task. In vertical tapping, CNN and DNN demonstrated stable performance with approximately 85% accuracy, while SVM slightly trailed with around 80% accuracy. However, in horizontal tapping, all three models achieved perfect classification with accuracy, precision, recall, and F1-score reaching 100%. This study demonstrates the effective use of acoustic response as input for Deep Learning models to distinguish between fresh and rotten eggs. The findings highlight the potential application of this technology in the food industry to ensure product quality before consumption, with significant implications for developing reliable automated solutions. Future research could expand validation using larger datasets and optimize sensor usage and data processing techniques to enhance detection consistency and reliability.

Radiated Sound and Transmitted Vibration Following the Ball/Racket Impact of a Tennis Serve

Shock-induced vibrations transmitted from the racket to the tennis player’s upper limb have interested researchers, whether for investigating their effect on injury risk, or for designing new equipment. Measuring these vibrations is, however, very challenging in an ecological playing situation: sensors must be of very high quality in order to precisely measure high-energy and broad-frequency signals, as well as non-invasive in order to allow the players to perform their usual movements. The working hypothesis of this paper is that contactless sound recordings of the ball/racket impact carry the same information as direct vibratory measurements. The present study focuses on the tennis serve, as being tennis’ most energy-demanding stroke, therefore possibly being the most traumatic stroke for the upper limb. This article aims (a) to evaluate the propagation of vibration from the racket to the upper limb; and (b) to identify correlations with acoustic signals collected simultaneously. Eight expert tennis players performed serves with three rackets and two ball spin effects. Accelerometers measured the vibration on the racket and at five locations on the upper limb, and a microphone measured the impact sound. Resulting signals were analyzed in terms of energy and spectral descriptors. Results showed that flat serves produced louder sounds, higher vibration levels, lower acoustic spectral centroids, and higher vibratory spectral centroids than kick serves. The racket only had a marginal influence. Similarities between acoustic and vibratory measurements were found (levels were correlated), but so were differences (spectral centroids tended to be negatively correlated), encouraging further studies on the link between sound and vibration for the in situ measurement of shock-induced vibration.

Emergency Vehicle Classification Using Combined Temporal and Spectral Audio Features with Machine Learning Algorithms

This study presents a novel approach to emergency vehicle classification that leverages a comprehensive set of informative audio features to distinguish between ambulance sirens, fire truck sirens, and traffic noise. A unique contribution lies in combining time domain features, including root mean square (RMS) and zero-crossing rate, to capture the temporal characteristics, like signal energy changes, with frequency domain features derived from short-time Fourier transform (STFT). These include spectral centroid, spectral bandwidth, and spectral roll-off, providing insights into the sound’s frequency content for differentiating siren patterns from traffic noise. Additionally, Mel-frequency cepstral coefficients (MFCCs) are incorporated to capture the human-like auditory perception of the spectral information. This combination captures both temporal and spectral characteristics of the audio signals, enhancing the model’s ability to discriminate between emergency vehicles and traffic noise compared to using features from a single domain. A significant contribution of this study is the integration of data augmentation techniques that replicate real-world conditions, including the Doppler effect and noise environment considerations. This study further investigates the effectiveness of different machine learning algorithms applied to the extracted features, performing a comparative analysis to determine the most effective classifier for this task. This analysis reveals that the support vector machine (SVM) achieves the highest accuracy of 99.5%, followed by random forest (RF) and k-nearest neighbors (KNNs) at 98.5%, while AdaBoost lags at 96.0% and long short-term memory (LSTM) has an accuracy of 93%. We also demonstrate the effectiveness of a stacked ensemble classifier, and utilizing these base learners achieves an accuracy of 99.5%. Furthermore, this study conducted leave-one-out cross-validation (LOOCV) to validate the results, with SVM and RF achieving accuracies of 98.5%, followed by KNN and AdaBoost, which are 97.0% and 90.5%. These findings indicate the superior performance of advanced ML techniques in emergency vehicle classification.

HEAR set: A ligHtwEight acoustic paRameters set to assess mental health from voice analysis

BackgroundVoice analysis has significant potential in aiding healthcare professionals with detecting, diagnosing, and personalising treatment. It represents an objective and non-intrusive tool for supporting the detection and monitoring of specific pathologies. By calculating various acoustic features, voice analysis extracts valuable information to assess voice quality. The choice of these parameters is crucial for an accurate assessment. MethodIn this paper, we propose a lightweight acoustic parameter set, named HEAR, able to evaluate voice quality to assess mental health. In detail, this consists of jitter, spectral centroid, Mel-frequency cepstral coefficients, and their derivates. The choice of parameters for the proposed set was influenced by the explainable significance of each acoustic parameter in the voice production process. ResultsThe reliability of the proposed acoustic set to detect the early symptoms of mental disorders was evaluated in an experimental phase. Voices of subjects suffering from different mental pathologies, selected from available databases, were analysed. The performance obtained from the HEAR features was compared with that obtained by analysing features selected from toolkits widely used in the literature, as with those obtained using learned procedures. The best performance in terms of MAE and RMSE was achieved for the detection of depression (5.32 and 6.24 respectively). For the detection of psychogenic dysphonia and anxiety, the highest accuracy rates were about 75 % and 97 %, respectively. ConclusionsThe comparative evaluation was carried out to assess the performance of the proposed approach, demonstrating a reliable capability to highlight affective physiological alterations of voice quality due to the considered mental disorders.

Spectral Features Analysis for Print Quality Prediction in Additive Manufacturing: An Acoustics-Based Approach.

Quality prediction in additive manufacturing (AM) processes is crucial, particularly in high-risk manufacturing sectors like aerospace, biomedicals, and automotive. Acoustic sensors have emerged as valuable tools for detecting variations in print patterns by analyzing signatures and extracting distinctive features. This study focuses on the collection, preprocessing, and analysis of acoustic data streams from a Fused Deposition Modeling (FDM) 3D-printed sample cube (10 mm × 10 mm × 5 mm). Time and frequency-domain features were extracted at 10-s intervals at varying layer thicknesses. The audio samples were preprocessed using the Harmonic-Percussive Source Separation (HPSS) method, and the analysis of time and frequency features was performed using the Librosa module. Feature importance analysis was conducted, and machine learning (ML) prediction was implemented using eight different classifier algorithms (K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Gaussian Naive Bayes (GNB), Decision Trees (DT), Logistic Regression (LR), Random Forest (RF), Extreme Gradient Boosting (XGB), and Light Gradient Boosting Machine (LightGBM)) for the classification of print quality based on the labeled datasets. Three-dimensional-printed samples with varying layer thicknesses, representing two print quality levels, were used to generate audio samples. The extracted spectral features from these audio samples served as input variables for the supervised ML algorithms to predict print quality. The investigation revealed that the mean of the spectral flatness, spectral centroid, power spectral density, and RMS energy were the most critical acoustic features. Prediction metrics, including accuracy scores, F-1 scores, recall, precision, and ROC/AUC, were utilized to evaluate the models. The extreme gradient boosting algorithm stood out as the top model, attaining a prediction accuracy of 91.3%, precision of 88.8%, recall of 92.9%, F-1 score of 90.8%, and AUC of 96.3%. This research lays the foundation for acoustic based quality prediction and control of 3D printed parts using Fused Deposition Modeling and can be extended to other additive manufacturing techniques.

Rigdelet neural network and improved partial reinforcement effect optimizer for music genre classification from sound spectrum images

In this paper, a new approach has been introduced for classifying the music genres. The proposed approach involves transforming an audio signal into a unified representation known as a sound spectrum, from which texture features have been extracted using an enhanced Rigdelet Neural Network (RNN). Additionally, the RNN has been optimized using an improved version of the partial reinforcement effect optimizer (IPREO) that effectively avoids local optima and enhances the RNN's generalization capability. The GTZAN dataset has been utilized in experiments to assess the effectiveness of the proposed RNN/IPREO model for music genre classification. The results show an impressive accuracy of 92 % by incorporating a combination of spectral centroid, Mel-spectrogram, and Mel-frequency cepstral coefficients (MFCCs) as features. This performance significantly outperformed K-Means (58 %) and Support Vector Machines (up to 68 %). Furthermore, the RNN/IPREO model outshined various deep learning architectures such as Neural Networks (65 %), RNNs (84 %), CNNs (88 %), DNNs (86 %), VGG-16 (91 %), and ResNet-50 (90 %). It is worth noting that the RNN/IPREO model was able to achieve comparable results to well-known deep models like VGG-16, ResNet-50, and RNN-LSTM, sometimes even surpassing their scores. This highlights the strength of its hybrid CNN–Bi-directional RNN design in conjunction with the IPREO parameter optimization algorithm for extracting intricate and sequential auditory data.

Assessment of Pepper Robot's Speech Recognition System through the Lens of Machine Learning.

Speech comprehension can be challenging due to multiple factors, causing inconvenience for both the speaker and the listener. In such situations, using a humanoid robot, Pepper, can be beneficial as it can display the corresponding text on its screen. However, prior to that, it is essential to carefully assess the accuracy of the audio recordings captured by Pepper. Therefore, in this study, an experiment is conducted with eight participants with the primary objective of examining Pepper's speech recognition system with the help of audio features such as Mel-Frequency Cepstral Coefficients, spectral centroid, spectral flatness, the Zero-Crossing Rate, pitch, and energy. Furthermore, the K-means algorithm was employed to create clusters based on these features with the aim of selecting the most suitable cluster with the help of the speech-to-text conversion tool Whisper. The selection of the best cluster is accomplished by finding the maximum accuracy data points lying in a cluster. A criterion of discarding data points with values of WER above 0.3 is imposed to achieve this. The findings of this study suggest that a distance of up to one meter from the humanoid robot Pepper is suitable for capturing the best speech recordings. In contrast, age and gender do not influence the accuracy of recorded speech. The proposed system will provide a significant strength in settings where subtitles are required to improve the comprehension of spoken statements.

Combining Transformer, Convolutional Neural Network, and Long Short-Term Memory Architectures: A Novel Ensemble Learning Technique That Leverages Multi-Acoustic Features for Speech Emotion Recognition in Distance Education Classrooms

Speech emotion recognition (SER) is a technology that can be applied to distance education to analyze speech patterns and evaluate speakers’ emotional states in real time. It provides valuable insights and can be used to enhance students’ learning experiences by enabling the assessment of their instructors’ emotional stability, a factor that significantly impacts the effectiveness of information delivery. Students demonstrate different engagement levels during learning activities, and assessing this engagement is important for controlling the learning process and improving e-learning systems. An important aspect that may influence student engagement is their instructors’ emotional state. Accordingly, this study used deep learning techniques to create an automated system for recognizing instructors’ emotions in their speech when delivering distance learning. This methodology entailed integrating transformer, convolutional neural network, and long short-term memory architectures into an ensemble to enhance the SER. Feature extraction from audio data used Mel-frequency cepstral coefficients; chroma; a Mel spectrogram; the zero-crossing rate; spectral contrast, centroid, bandwidth, and roll-off; and the root-mean square, with subsequent optimization processes such as adding noise, conducting time stretching, and shifting the audio data. Several transformer blocks were incorporated, and a multi-head self-attention mechanism was employed to identify the relationships between the input sequence segments. The preprocessing and data augmentation methodologies significantly enhanced the precision of the results, with accuracy rates of 96.3%, 99.86%, 96.5%, and 85.3% for the Ryerson Audio–Visual Database of Emotional Speech and Song, Berlin Database of Emotional Speech, Surrey Audio–Visual Expressed Emotion, and Interactive Emotional Dyadic Motion Capture datasets, respectively. Furthermore, it achieved 83% accuracy on another dataset created for this study, the Saudi Higher-Education Instructor Emotions dataset. The results demonstrate the considerable accuracy of this model in detecting emotions in speech data across different languages and datasets.

A Novel Time-frequency Representation Method: The Generalized W Transform

The time-frequency representation (TFR) of seismic data is an effective technology for the detection of hydrocarbon reservoirs. To obtain the TFR of a seismic trace, a mathematical transform tool must be used to perform the decomposition of the seismic trace. This paper introduces an effective time-frequency decomposition method: the generalized W transform (GWT). We prove that the GWT is not a strictly reversible mathematical transform. The numerical experiment of a simulated seismic trace shows that the reconstruction relative error of inverse GWT could reach up to 20%. Nevertheless, the time-frequency spectrum obtained from its forward transform is particularly suitable for identifying oil and gas reservoirs. The presented GWT has three advantages: (1) Its time-frequency spectrum has a high temporal resolution even at low frequencies; (2) The spectral centroid corresponds to the peak frequency of the wavelet; (3) It eliminates the singularity of the original W transform (WT) at the peak frequency of the waveform. Compared with the wavelet transform and the S transform, the generalized W transform can more accurately characterize reservoirs. A real data example illustrates that the GWT provides better TFR performance and can more effectively identify hydrocarbon reservoirs.

Wind Profile Reconstruction Based on Convolutional Neural Network for Incoherent Doppler Wind LiDAR

The rapid development of artificial intelligence (AI) and deep learning has revolutionized the field of data analysis in recent years, including signal data acquired by remote sensors. Light Detection and Ranging (LiDAR) technology is widely used in atmospheric research for measuring various atmospheric parameters. Wind measurement using LiDAR data has traditionally relied on the spectral centroid (SC) algorithm. However, this approach has limitations in handling LiDAR data, particularly in low signal-to-noise ratio (SNR) regions. To overcome these limitations, this study leverages the capabilities of customized deep-learning techniques to achieve accurate wind profile reconstruction. The study uses datasets obtained from the European Centre for Medium Weather Forecasting (ECMWF) Reanalysis v5 (ERA5) and the mobile Incoherent Doppler LiDAR (ICDL) system constructed by the University of Science and Technology of China. We present a simulation-based approach for generating wind profiles from the statistical data and the associated theoretical calculations. Whereafter, our team constructed a convolutional neural network (CNN) model based on the U-Net architecture to replace the SC algorithm for LiDAR data post-processing. The CNN-generated results are evaluated and compared with the SC results and the ERA5 data. This study highlights the potential of deep learning-based techniques in atmospheric research and their ability to provide more accurate and reliable results.

Leaf‐density estimation for fruit‐tree canopy based on wind‐excited audio

AbstractIt is important to obtain real‐time leaf density of fruit‐tree canopies for the precision spray control of plant‐protection robots. However, conventional detection techniques for the characteristics of fruit‐tree canopies cannot acquire the canopy internal information, which may provide an unsatisfactory accuracy of detection of leaf densities. This paper proposes a method for estimating canopy leaf density of fruit trees based on wind‐excited audio. A wind‐exciting implement was used to force fruit‐tree canopy leaves vibrating to produce audio. Then, some correlation analysis methods were used to extract key characteristic parameters of wind‐excited audio that were significantly correlated with leaf density. Finally, based on the data set of wind‐excited audio, a few machine‐learning methods were used to develop leaf‐density estimation models. Test results showed that: (1) there were five key feature parameters of wind‐excited audio that were significantly correlated with leaf density: the short‐time energy, spectral centroid, the frequency average energy, the peak frequency, and the standard deviation of frequency. (2) the estimation model of leaf density developed based on backpropagation neural network for fruit‐tree canopy showed the optimal estimation results, which can achieve the estimation of leaf density of fruit‐tree canopies accurately. The overall correlation coefficient (R) of the estimation model was more than 0.84, the root‐mean‐square error was less than 0.73 m2 m−3, and the mean absolute error was less than 0.53 m2 m−3. This study is expected to provide a technical solution for the leaf‐density detection of fruit‐tree canopies of plant‐protection robots.

Acoustic Detection of Vaccine Reactions in Hens for Assessing Anti-Inflammatory Product Efficacy

Acoustic studies on poultry show that chicken vocalizations can be a real-time indicator of the health conditions of the birds and can improve animal welfare and farm management. In this study, hens vaccinated against infectious laryngotracheitis (ILT) were acoustically recorded for 3 days before vaccine administration (pre-reaction period) and also from vaccination onwards, with the first 5 days being identified as the “reaction period” and the 5 following days as “post reaction”. The raw audio was pre-processed to isolate hen calls and the 13 Mel-frequency cepstral coefficients; then, the spectral centroid and the number of vocalizations were extracted to build the acoustic dataset. The experiment was carried out on the same farm but in two different houses. The hens from one house were assigned to the control group, without administration of the anti-inflammatory product, and the other formed the treatment group. Both acoustic data sets were recorded and processed in the same way. The control group was used to acoustically model the animal reaction to the vaccine and we automatically detected the hens’ vaccine reactions and side effects through acoustics. From Scikit-Learn algorithms, Gaussian Naive Bayes was the best performing model, with a balanced accuracy of 80% for modeling the reactions and non-reactions caused by ILT in the control group. Furthermore, the importance of algorithm permutation highlighted that the centroid and MFCC4 were the most important features in acoustically detecting the ILT vaccine reaction. The fitted Gaussian Naive Bayes model allowed us to evaluate the treatment group to determine if the vocalizations after vaccine administration were detected as non-reactions, due to the anti-inflammatory product’s effectiveness. Of the sample, 99% of vocalizations were classified as non-reactions, due to the anti-inflammatory properties of the product, which reduced vaccine reactions and side effects. The non-invasive detection of hens’ responses to vaccination to prevent respiratory problems in hens described in this paper is an innovative method of measuring and detecting avian welfare.

Effective modelling of human expressive states from voice by adaptively tuning the neuro-fuzzy inference system

<span lang="EN-US">This paper aims to develop efficient speech-expressive models using the adaptively tuning neuro-fuzzy inference system (ANFIS). The developed models differentiate a high-arousal happiness state from a low-arousal sadness state from the benchmark Berlin (EMODB) database. The proposed low-cost flexible developed algorithms are self-tunable and can address several vivid real-world issues such as home tutoring, banking, and finance sectors, criminal investigations, psychological studies, call centers, cognitive and biomedical sciences. The work develops the proposed structures by formulating several novel feature vectors comprising both time and frequency information. The features considered are pitch (F0), the standard deviation of pitch (SDF0), autocorrelation coefficient (AC), log-energy (E), jitter, shimmer, harmonic to noise ratio (HNR), spectral centroid (SC), spectral roll-off (SR), spectral flux (SF), and zero-crossing rate (ZCR). to alleviate the issues of the curse of dimensionality associated with the frame-level extraction, the features are extracted at the utterance level. Several performance parameters have been computed to validate the individual time and frequency models. Further, the ANFIS models are tested for their efficacy in a combinational platform. The chosen features are complementary and the augmented vectors have indeed shown improved performance with more available information as revealed by our results.</span>

Auditory brightness in room reverberation

This work examines the impact of room reverberation on the auditory perceptual brightness of sounds. We hypothesized that room size would impact the perception of brightness, with smaller rooms (less reverberant) leading to sounds being perceived as more bright than larger rooms. We generated single-note instrument sounds from five different instruments using Logic Pro which were reverberated in three different-sized simulated rooms. Reverberant stimuli were presented in sequential room-size pairs (small-medium, small-large, medium-large) in a randomized order. Participants (15 musicians) were asked to rate the brightness of the second sound as compared with the first using a Likert-style scale, and the stimuli were blocked by instrument such that in each block a participant would only hear room-size comparisons of one instrument. Results were analyzed using an ordered-probit regression of the brightness ratings against the spectral centroid of the stimuli. We found no clear effect of room size. However, brightness ratings were weakly correlated with the average spectral centroid as shown in previous literature, and a stronger correlation was found with the steady-state portion of the sound. This suggests room size has little effect on brightness. Future work should examine the effect of different segments (e.g., attack, steady-state) on perceived brightness.

Acoustic detection of the effects of prolonged fasting on newly hatched broiler chickens

Water and food deprivation during the first few hours of life can act as a significant stressor for birds, as it can negatively affect their physical and immunological development. By providing essential nutrients, new enriched hydrated gels help alleviate the potential risks associated with prolonged fasting periods. Broiler chickens vocalisations are considered reliable indicators of changes in stress, anxiety and well-being. In this study, the results of recorded broiler vocalisations are presented together with a statistical analysis of the acoustic parameterisation. We focused on the hours preceding the transport of chicks from the hatchery to the breeding farm, dividing the animals into a control group that replicated real conditions, and a treatment group with the administration of a hydrated gel. The objectives of this study were to validate the effectiveness of continuous audio recording in monitoring stress level in food-deprived chicks, and to identify the most significant acoustic parameters. The selection of the acoustic parameters was based on a previous study conducted on broiler farms, which showed a strong linear relationship between the number of vocalisations, spectral centroid, and the bandwidth. Significant differences were observed between the first and last three hours. Furthermore, 8 h after gel ingestion, vocalisations indicated reduced stress levels.

Deep Learning for Neuromuscular Control of Vocal Source for Voice Production.

A computational neuromuscular control system that generates lung pressure and three intrinsic laryngeal muscle activations (cricothyroid, thyroarytenoid, and lateral cricoarytenoid) to control the vocal source was developed. In the current study, LeTalker, a biophysical computational model of the vocal system was used as the physical plant. In the LeTalker, a three-mass vocal fold model was used to simulate self-sustained vocal fold oscillation. A constant/ǝ/vowel was used for the vocal tract shape. The trachea was modeled after MRI measurements. The neuromuscular control system generates control parameters to achieve four acoustic targets (fundamental frequency, sound pressure level, normalized spectral centroid, and signal-to-noise ratio) and four somatosensory targets (vocal fold length, and longitudinal fiber stress in the three vocal fold layers). The deep-learning-based control system comprises one acoustic feedforward controller and two feedback (acoustic and somatosensory) controllers. Fifty thousand steady speech signals were generated using the LeTalker for training the control system. The results demonstrated that the control system was able to generate the lung pressure and the three muscle activations such that the four acoustic and four somatosensory targets were reached with high accuracy. After training, the motor command corrections from the feedback controllers were minimal compared to the feedforward controller except for thyroarytenoid muscle activation.