Performance Assessment of ChatGPT versus Bard in Detecting Alzheimer's Dementia.

Large language models (LLMs) find increasing applications in many fields. Here, three LLM chatbots (ChatGPT-3.5, ChatGPT-4, and Bard) are assessed in their current form, as publicly available, for their ability to recognize Alzheimer's dementia (AD) and Cognitively Normal (CN) individuals using textual input derived from spontaneous speech recordings. A zero-shot learning approach is used at two levels of independent queries, with the second query (chain-of-thought prompting) eliciting more detailed information than the first. Each LLM chatbot's performance is evaluated on the prediction generated in terms of accuracy, sensitivity, specificity, precision, and F1 score. LLM chatbots generated a three-class outcome ("AD", "CN", or "Unsure"). When positively identifying AD, Bard produced the highest true-positives (89% recall) and highest F1 score (71%), but tended to misidentify CN as AD, with high confidence (low "Unsure" rates); for positively identifying CN, GPT-4 resulted in the highest true-negatives at 56% and highest F1 score (62%), adopting a diplomatic stance (moderate "Unsure" rates). Overall, the three LLM chatbots can identify AD vs. CN, surpassing chance-levels, but do not currently satisfy the requirements for clinical application.

Acoustic characterization of nanofibers for optimization with porous substrate.

Nanofiber-porous systems comprising a porous substrate overlaid with nanofiber weave offer the potential for higher acoustic absorption than the substrate alone with negligible increase in thickness. The characterization of nanofibers from acoustic measurements is investigated in this work, and a regression model for predicting their acoustic properties from a single physical parameter is proposed to enable the design of nanofiber-porous systems directly from fabrication parameters. Characterization as a resistive screen via Johnson-Champoux-Allard and lumped element models for transfer matrix computations of absorption coefficient for nanofiber-porous systems exhibited good agreement with the measured spectra. The lumped element model was chosen as it was defined by fewer parameters and did not require nanofiber layer thickness measurements, eliminating the associated uncertainty. A regression model for lumped element parameters vs areal density established a design tool based on a single, easily measured physical property for optimized absorption at target frequencies without prior acoustic characterization of the nanofiber layer, enabling the analysis of complex acoustic networks incorporating nanofiber-porous systems. Practical considerations of applying adhesives at the nanofiber-porous interface were studied to evaluate possible enhancement of acoustic performance. For comparison with prior work by others, flow resistances from physical measurement and acoustic characterization were compared.

Vocal Tract Resonance Detection at Low Frequencies: Improving Physical and Transducer Configurations.

Broadband excitation introduced at the speaker's lips and the evaluation of its corresponding relative acoustic impedance spectrum allow for fast, accurate and non-invasive estimations of vocal tract resonances during speech and singing. However, due to radiation impedance interactions at the lips at low frequencies, it is challenging to make reliable measurements of resonances lower than 500 Hz due to poor signal to noise ratios, limiting investigations of the first vocal tract resonance using such a method. In this paper, various physical configurations which may optimize the acoustic coupling between transducers and the vocal tract are investigated and the practical arrangement which yields the optimal vocal tract resonance detection sensitivity at low frequencies is identified. To support the investigation, two quantitative analysis methods are proposed to facilitate comparison of the sensitivity and quality of resonances identified. Accordingly, the optimal configuration identified has better acoustic coupling and low-frequency response compared with existing arrangements and is shown to reliably detect resonances down to 350 Hz (and possibly lower), thereby allowing the first resonance of a wide range of vowel articulations to be estimated with confidence.

Development and Validation of a Deep Learning System for Sound-based Prediction of Urinary Flow.

BACKGROUND: Uroflowmetry remains an important tool for the assessment of patients with lower urinary tract symptoms (LUTS), but accuracy can be limited by within-subject variation of urinary flow rates. Voiding acoustics appear to correlate well with conventional uroflowmetry and show promise as a convenient home-based alternative for the monitoring of urinary flows. OBJECTIVE: To evaluate the ability of a sound-based deep learning algorithm (Audioflow) to predict uroflowmetry parameters and identify abnormal urinary flow patterns. DESIGN, SETTING, AND PARTICIPANTS: In this prospective open-label study, 534 male participants recruited at Singapore General Hospital between December 1, 2017 and July 1, 2019 voided into a uroflowmetry machine, and voiding acoustics were recorded using a smartphone in close proximity. The Audioflow algorithm consisted of two models-the first model for the prediction of flow parameters including maximum flow rate (Qmax), average flow rate (Qave), and voided volume (VV) was trained and validated using leave-one-out cross-validation procedures; the second model for discrimination of normal and abnormal urinary flows was trained based on a reference standard created by three senior urologists. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Lin's correlation coefficient was used to evaluate the agreement between Audioflow predictions and conventional uroflowmetry for Qmax, Qave, and VV. Accuracy of the Audioflow algorithm in the identification of abnormal urinary flows was assessed with sensitivity analyses and the area under the receiver operating curve (AUC); this algorithm was compared with an external panel of graders comprising six urology residents/general practitioners who separately graded flow patterns in the validation dataset. RESULTS AND LIMITATIONS: A total of 331 patients were included for analysis. Agreement between Audioflow and conventional uroflowmetry for Qmax, Qave, and VV was 0.77 (95% confidence interval [CI], 0.72-0.80), 0.85 (95% CI, 0.82-0.88) and 0.84 (95% CI, 0.80-0.87), respectively. For the identification of abnormal flows, Audioflow achieved a high rate of agreement of 83.8% (95% CI, 77.5-90.1%) with the reference standard, and was comparable with an external panel of six residents/general practitioners. AUC was 0.892 (95% CI, 0.834-0.951), with high sensitivity of 87.3% (95% CI, 76.8-93.7%) and specificity of 77.5% (95% CI, 61.1-88.6%). CONCLUSIONS: The results of this study suggest that a deep learning algorithm can predict uroflowmetry parameters and identify abnormal urinary voids based on voiding sounds, and shows promise as a simple home-based alternative to uroflowmetry in the management of patients with LUTS. PATIENT SUMMARY: In this study, we trained a deep learning-based algorithm to measure urinary flow rates and identify abnormal flow patterns based on voiding sounds. This may provide a convenient, home-based alternative to conventional uroflowmetry for the assessment and monitoring of patients with lower urinary tract symptoms.

Estimating vocal tract geometry from acoustic impedance using deep neural network.

A data-driven approach using artificial neural networks is proposed to address the classic inverse area function problem, i.e., to determine the vocal tract geometry (modelled as a tube of nonuniform cylindrical cross-sections) from the vocal tract acoustic impedance spectrum. The predicted cylindrical radii and the actual radii were found to have high correlation in the three- and four-cylinder model (Pearson coefficient (ρ) and Lin concordance coefficient (ρc) exceeded 95%); however, for the six-cylinder model, the correlation was low (ρ around 75% and ρc around 69%). Upon standardizing the impedance value, the correlation improved significantly for all cases (ρ and ρc exceeded 90%).

Deep Neural Network-Based Respiratory Pathology Classification Using Cough Sounds.

Intelligent systems are transforming the world, as well as our healthcare system. We propose a deep learning-based cough sound classification model that can distinguish between children with healthy versus pathological coughs such as asthma, upper respiratory tract infection (URTI), and lower respiratory tract infection (LRTI). To train a deep neural network model, we collected a new dataset of cough sounds, labelled with a clinician's diagnosis. The chosen model is a bidirectional long-short-term memory network (BiLSTM) based on Mel-Frequency Cepstral Coefficients (MFCCs) features. The resulting trained model when trained for classifying two classes of coughs-healthy or pathology (in general or belonging to a specific respiratory pathology)-reaches accuracy exceeding 84% when classifying the cough to the label provided by the physicians' diagnosis. To classify the subject's respiratory pathology condition, results of multiple cough epochs per subject were combined. The resulting prediction accuracy exceeds 91% for all three respiratory pathologies. However, when the model is trained to classify and discriminate among four classes of coughs, overall accuracy dropped: one class of pathological coughs is often misclassified as the other. However, if one considers the healthy cough classified as healthy and pathological cough classified to have some kind of pathology, then the overall accuracy of the four-class model is above 84%. A longitudinal study of MFCC feature space when comparing pathological and recovered coughs collected from the same subjects revealed the fact that pathological coughs, irrespective of the underlying conditions, occupy the same feature space making it harder to differentiate only using MFCC features.

Acoustic Effect of Face Mask Design and Material Choice.

The widespread adoption of face masks is now a standard public health response to the 2020 pandemic. Although studies have shown that wearing a face mask interferes with speech and intelligibility, relating the acoustic response of the mask to design parameters such as fabric choice, number of layers and mask geometry is not well understood. Using a dummy head mounted with a loudspeaker at its mouth generating a broadband signal, we report the acoustic response associated with 10 different masks (different material/design) and the effect of material layers; a small number of masks were found to be almost acoustically transparent (minimal losses). While different mask material and design result in different frequency responses, we find that material selection has somewhat greater influence on transmission characteristics than mask design or geometry choices. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s40857-021-00245-2.

Asthmatic versus healthy child classification based on cough and vocalised /ɑ:/ sounds.

Cough is a common symptom presenting in asthmatic children. In this investigation, an audio-based classification model is presented that can differentiate between healthy and asthmatic children, based on the combination of cough and vocalised /ɑ:/ sounds. A Gaussian mixture model using mel-frequency cepstral coefficients and constant-Q cepstral coefficients was trained. When comparing the predicted labels with the clinician's diagnosis, this cough sound model reaches an overall accuracy of 95.3%. The vocalised /ɑ:/ model reaches an accuracy of 72.2%, which is still significant because the dataset contains only 333 /ɑ:/ sounds versus 2029 cough sounds.

Perceptual evaluation of measures of spectral variance.

In many applications, it is desirable to achieve a signal that is as close as possible to ideal white noise. One example is in the design of an artificial reverberator, whereby there is a need for its lossless prototype output from an impulse input to be perceptually white as much as possible. The Ljung-Box test, the Drouiche test, and the Wiener Entropy-also called the Spectral Flatness Measure-are three well-known methods for quantifying the similarity of a given signal to ideal white noise. In this paper, listening tests are conducted to measure the Just Noticeable Difference (JND) on the perception of white noise, which is the JND between ideal Gaussian white noise and noise with a specified deviation from the flat spectrum. This paper reports the JND values using one of these measures of whiteness, which is the Ljung-Box test. This paper finds considerable disagreement between the Ljung-Box test and the other two methods and shows that none of the methods is a significantly better predictor of listeners' perception of whiteness. This suggests a need for a whiteness test that is more closely correlated to human perception.

The effect of nearby timpani strokes on horn playing.

Horn players have observed that timpani strokes can interfere disruptively with their playing, especially when they are seated close to the timpani. Measuring the horn's transfer function in the bell-to-mouthpiece direction reveals that the horn behaves as an acoustic impedance matching device, capable of transmitting waves with pressure gains of at least 20 dB near horn playing resonances. During moderate to loud timpani strokes, the horn transmits an overall impulse gain response of at least 16 dB from the bell to the mouthpiece, while evidence of non-linear bore propagation can be observed for louder strokes. If the timpani is tuned near a horn resonance, as is usually the case, further bore resonance interactions may be observed leading to gains of ∼26 dB from bell to mouthpiece. Finally, measurements of horn playing made under conditions approximating playing reveal that timpani strokes sounding near the horn bell are capable of disrupting horn playing by affecting the amplitude, periodicity, and frequency of the pressure signal generated at the horn player's lips.

Do trumpet players tune resonances of the vocal tract?

The acoustic impedance spectrum was measured in the mouths of seven trumpeters while they played normal notes and while they practiced "bending" the pitch below or above the normal value. The peaks in vocal tract impedance usually had magnitudes rather smaller than those of the bore of the trumpet. Over the range measured, none of the trumpeters showed systematic tuning of the resonances of the vocal tract. However, all players commented that the presence of the impedance head in the mouth prevented them from playing the very highest notes of which they were normally capable. It is therefore possible that these players might use either resonance tuning or perhaps very high impedance magnitudes for some notes beyond the measured range. The observed lack of tuning contrasts with measurements for the saxophone which, like the trumpet, has weak resonances in the third and fourth octaves. Saxophonists are only able to play the highest range by tuning resonances of the vocal tract, so that the series impedance has a very strong peak at a frequency near that of the desired note. This difference is explained by the greater control that the trumpet player has over the natural frequency of the vibrating valve.

Saxophonists tune vocal tract resonances in advanced performance techniques.

The acoustical impedance spectrum was measured in the mouths of saxophonists while they played. During bugling and while playing in the very high or altissimo range, experienced players tune a strong, but relatively broad, peak in the tract impedance to select which peak in the bore impedance will determine the note. Less experienced players are unable to produce resonances with impedance peaks comparable in magnitude to those of the bore and consequently are unable to play these notes. Experienced players can also tune their tracts to select which combinations of notes are played simultaneously in multiphonics or chords, and to produce pitch bending, a technique in which notes are produced at frequencies far from those of the peak of impedance of the instrument bore. However, in normal playing in the standard range, there is no consistent tuning of the tract resonances. The playing frequency, in all cases, lies close to the peak in the impedance of the reed in parallel with the series combination of the impedances measured in the mouth and the instrument bore on either side of the reed (ZMouth+ZBore)∥ZReed.

Pitch bending and glissandi on the clarinet: roles of the vocal tract and partial tone hole closure.

Clarinettists combine non-standard fingerings with particular vocal tract configurations to achieve pitch bending, i.e., sounding pitches that can deviate substantially from those of standard fingerings. Impedance spectra were measured in the mouth of expert clarinettists while they played normally and during pitch bending, using a measurement head incorporated within a functioning clarinet mouthpiece. These were compared with the input impedance spectra of the clarinet for the fingerings used. Partially uncovering a tone hole by sliding a finger raises the frequency of clarinet impedance peaks, thereby allowing smooth increases in sounding pitch over some of the range. To bend notes in the second register and higher, however, clarinettists produce vocal tract resonances whose impedance maxima have magnitudes comparable with those of the bore resonance, which then may influence or determine the sounding frequency. It is much easier to bend notes down than up because of the phase relations of the bore and tract resonances, and the compliance of the reed. Expert clarinettists performed the glissando opening of Gershwin's 'Rhapsody in Blue'. Here, players coordinate the two effects: They slide their fingers gradually over open tone holes, while simultaneously adjusting a strong vocal tract resonance to the desired pitch.

Experienced saxophonists learn to tune their vocal tracts.

Acousticians have long debated whether and how the resonances of the vocal tract are involved in the playing of clarinet and saxophone. We measured the resonances of saxophonists' vocal tracts directly while they played. Over most of the instrument's range, there is no simple relation between tract resonances and the note played, and the tract resonances varied among players. In the high (altissimo) range, a strong resonance of the tracts of professional saxophonists was systematically tuned slightly above the desired note. Amateurs, who did not tune a strong resonance, were unable to play notes in the altissimo range.