BACKGROUND: The digital era has witnessed an escalating dependence on digital platforms for news and information, coupled with the advent of \"deepfake\" technology. Deepfakes, leveraging deep learning models on extensive data sets of voice recordings and images, pose substantial threats to media authenticity, potentially leading to unethical misuse such as impersonation and the dissemination of false information.
OBJECTIVE: To counteract this challenge, this study aims to introduce the concept of innate biological processes to discern between authentic human voices and cloned voices. We propose that the presence or absence of certain perceptual features, such as pauses in speech, can effectively distinguish between cloned and authentic audio.
METHODS: A total of 49 adult participants representing diverse ethnic backgrounds and accents were recruited. Each participant contributed voice samples for the training of up to 3 distinct voice cloning text-to-speech models and 3 control paragraphs. Subsequently, the cloning models generated synthetic versions of the control paragraphs, resulting in a data set consisting of up to 9 cloned audio samples and 3 control samples per participant. We analyzed the speech pauses caused by biological actions such as respiration, swallowing, and cognitive processes. Five audio features corresponding to speech pause profiles were calculated. Differences between authentic and cloned audio for these features were assessed, and 5 classical machine learning algorithms were implemented using these features to create a prediction model. The generalization capability of the optimal model was evaluated through testing on unseen data, incorporating a model-naive generator, a model-naive paragraph, and model-naive participants.
RESULTS: Cloned audio exhibited significantly increased time between pauses (P<.001), decreased variation in speech segment length (P=.003), increased overall proportion of time speaking (P=.04), and decreased rates of micro- and macropauses in speech (both P=.01). Five machine learning models were implemented using these features, with the AdaBoost model demonstrating the highest performance, achieving a 5-fold cross-validation balanced accuracy of 0.81 (SD 0.05). Other models included support vector machine (balanced accuracy 0.79, SD 0.03), random forest (balanced accuracy 0.78, SD 0.04), logistic regression, and decision tree (balanced accuracies 0.76, SD 0.10 and 0.72, SD 0.06). When evaluating the optimal AdaBoost model, it achieved an overall test accuracy of 0.79 when predicting unseen data.
CONCLUSIONS: The incorporation of perceptual, biological features into machine learning models demonstrates promising results in distinguishing between authentic human voices and cloned audio.

BACKGROUND: Vocal biomarkers, derived from acoustic analysis of vocal characteristics, offer noninvasive avenues for medical screening, diagnostics, and monitoring. Previous research demonstrated the feasibility of predicting type 2 diabetes mellitus through acoustic analysis of smartphone-recorded speech. Building upon this work, this study explores the impact of audio data compression on acoustic vocal biomarker development, which is critical for broader applicability in health care.
OBJECTIVE: The objective of this research is to analyze how common audio compression algorithms (MP3, M4A, and WMA) applied by 3 different conversion tools at 2 bitrates affect features crucial for vocal biomarker detection.
METHODS: The impact of audio data compression on acoustic vocal biomarker development was investigated using uncompressed voice samples converted into MP3, M4A, and WMA formats at 2 bitrates (320 and 128 kbps) with MediaHuman (MH) Audio Converter, WonderShare (WS) UniConverter, and Fast Forward Moving Picture Experts Group (FFmpeg). The data set comprised recordings from 505 participants, totaling 17,298 audio files, collected using a smartphone. Participants recorded a fixed English sentence up to 6 times daily for up to 14 days. Feature extraction, including pitch, jitter, intensity, and Mel-frequency cepstral coefficients (MFCCs), was conducted using Python and Parselmouth. The Wilcoxon signed rank test and the Bonferroni correction for multiple comparisons were used for statistical analysis.
RESULTS: In this study, 36,970 audio files were initially recorded from 505 participants, with 17,298 recordings meeting the fixed sentence criteria after screening. Differences between the audio conversion software, MH, WS, and FFmpeg, were notable, impacting compression outcomes such as constant or variable bitrates. Analysis encompassed diverse data compression formats and a wide array of voice features and MFCCs. Wilcoxon signed rank tests yielded P values, with those below the Bonferroni-corrected significance level indicating significant alterations due to compression. The results indicated feature-specific impacts of compression across formats and bitrates. MH-converted files exhibited greater resilience compared to WS-converted files. Bitrate also influenced feature stability, with 38 cases affected uniquely by a single bitrate. Notably, voice features showed greater stability than MFCCs across conversion methods.
CONCLUSIONS: Compression effects were found to be feature specific, with MH and FFmpeg showing greater resilience. Some features were consistently affected, emphasizing the importance of understanding feature resilience for diagnostic applications. Considering the implementation of vocal biomarkers in health care, finding features that remain consistent through compression for data storage or transmission purposes is valuable. Focused on specific features and formats, future research could broaden the scope to include diverse features, real-time compression algorithms, and various recording methods. This study enhances our understanding of audio compression\'s influence on voice features and MFCCs, providing insights for developing applications across fields. The research underscores the significance of feature stability in working with compressed audio data, laying a foundation for informed voice data use in evolving technological landscapes.

BACKGROUND: High-frequency hearing loss is one of the most common problems in the aging population and with those who have a history of exposure to loud noises. This type of hearing loss can be frustrating and disabling, making it difficult to understand speech communication and interact effectively with the world.
OBJECTIVE: This study aimed to examine the impact of spatially unique haptic vibrations representing high-frequency phonemes on the self-perceived ability to understand conversations in everyday situations.
METHODS: To address high-frequency hearing loss, a multi-motor wristband was developed that uses machine learning to listen for specific high-frequency phonemes. The wristband vibrates in spatially unique locations to represent which phoneme was present in real time. A total of 16 participants with high-frequency hearing loss were recruited and asked to wear the wristband for 6 weeks. The degree of disability associated with hearing loss was measured weekly using the Abbreviated Profile of Hearing Aid Benefit (APHAB).
RESULTS: By the end of the 6-week study, the average APHAB benefit score across all participants reached 12.39 points, from a baseline of 40.32 to a final score of 27.93 (SD 13.11; N=16; P=.002, 2-tailed dependent t test). Those without hearing aids showed a 10.78-point larger improvement in average APHAB benefit score at 6 weeks than those with hearing aids (t14=2.14; P=.10, 2-tailed independent t test). The average benefit score across all participants for ease of communication was 15.44 (SD 13.88; N=16; P<.001, 2-tailed dependent t test). The average benefit score across all participants for background noise was 10.88 (SD 17.54; N=16; P=.03, 2-tailed dependent t test). The average benefit score across all participants for reverberation was 10.84 (SD 16.95; N=16; P=.02, 2-tailed dependent t test).
CONCLUSIONS: These findings show that vibrotactile sensory substitution delivered by a wristband that produces spatially distinguishable vibrations in correspondence with high-frequency phonemes helps individuals with high-frequency hearing loss improve their perceived understanding of verbal communication. Vibrotactile feedback provides benefits whether or not a person wears hearing aids, albeit in slightly different ways. Finally, individuals with the greatest perceived difficulty understanding speech experienced the greatest amount of perceived benefit from vibrotactile feedback.

UNASSIGNED: The use of a smartphone built-in microphone for auscultation is a feasible alternative to the use of a stethoscope, when applied by physicians.
UNASSIGNED: This cross-sectional study aims to assess the feasibility of this technology when used by parents-the real intended end users.
UNASSIGNED: Physicians recruited 46 children (male: n=33, 72%; age: mean 11.3, SD 3.1 y; children with asthma: n=24, 52%) during medical visits in a pediatric department of a tertiary hospital. Smartphone auscultation using an app was performed at 4 locations (trachea, right anterior chest, and right and left lung bases), first by a physician (recordings: n=297) and later by a parent (recordings: n=344). All recordings (N=641) were classified by 3 annotators for quality and the presence of adventitious sounds. Parents completed a questionnaire to provide feedback on the app, using a Likert scale ranging from 1 (\"totally disagree\") to 5 (\"totally agree\").
UNASSIGNED: Most recordings had quality (physicians\' recordings: 253/297, 85.2%; parents\' recordings: 266/346, 76.9%). The proportions of physicians\' recordings (34/253, 13.4%) and parents\' recordings (31/266, 11.7%) with adventitious sounds were similar. Parents found the app easy to use (questionnaire: median 5, IQR 5-5) and were willing to use it (questionnaire: median 5, IQR 5-5).
UNASSIGNED: Our results show that smartphone auscultation is feasible when performed by parents in the clinical context, but further investigation is needed to test its feasibility in real life.

UNASSIGNED: The exposure to some environmental sounds has detrimental effects on health and might affect the performance in cognitive tasks. In this study, we analyze the effect of the neighborhood noises of a baby crying and dogs barking on the autonomic response and cognitive function.
UNASSIGNED: Twenty participants were exposed, in separate sessions, to white noise, a baby crying, a small dog barking, and a large dog barking. During each session, heart rate, skin conductance, reaction times, spatial memory, and mathematical processing measures were taken throughout time.
UNASSIGNED: The sounds of a baby crying and dogs barking led to significantly higher heart rates and skin conductance levels as opposed to exposure to white noise. Results were not as consistent with exposure to barking as they were to the baby. Exposure to the baby crying and dogs barking led to faster reaction times, possibly due to a facilitation by the autonomic system activation. No significant effects on spatial memory were found. Conversely, participants performed worse and slower in a mathematical task when exposed to the dog and baby sounds, than when exposed to control noise.
UNASSIGNED: Exposure to the sound of crying babies and dogs barking leads to increased sympathetic response and decreased cognitive ability, as compared to exposure to control sounds. Special attention should be paid to the mitigation of exposure to these types of noises.

High-frequency hearing loss is one of the most common problems in the aging population and with those who have a history of exposure to loud noises. This type of hearing loss can be frustrating and disabling, making it difficult to understand speech communication and interact effectively with the world.
This study aimed to examine the impact of spatially unique haptic vibrations representing high-frequency phonemes on the self-perceived ability to understand conversations in everyday situations.
To address high-frequency hearing loss, a multi-motor wristband was developed that uses machine learning to listen for specific high-frequency phonemes. The wristband vibrates in spatially unique locations to represent which phoneme was present in real time. A total of 16 participants with high-frequency hearing loss were recruited and asked to wear the wristband for 6 weeks. The degree of disability associated with hearing loss was measured weekly using the Abbreviated Profile of Hearing Aid Benefit (APHAB).
By the end of the 6-week study, the average APHAB benefit score across all participants reached 12.39 points, from a baseline of 40.32 to a final score of 27.93 (SD 13.11; N=16; P=.002, 2-tailed dependent t test). Those without hearing aids showed a 10.78-point larger improvement in average APHAB benefit score at 6 weeks than those with hearing aids (t14=2.14; P=.10, 2-tailed independent t test). The average benefit score across all participants for ease of communication was 15.44 (SD 13.88; N=16; P<.001, 2-tailed dependent t test). The average benefit score across all participants for background noise was 10.88 (SD 17.54; N=16; P=.03, 2-tailed dependent t test). The average benefit score across all participants for reverberation was 10.84 (SD 16.95; N=16; P=.02, 2-tailed dependent t test).
These findings show that vibrotactile sensory substitution delivered by a wristband that produces spatially distinguishable vibrations in correspondence with high-frequency phonemes helps individuals with high-frequency hearing loss improve their perceived understanding of verbal communication. Vibrotactile feedback provides benefits whether or not a person wears hearing aids, albeit in slightly different ways. Finally, individuals with the greatest perceived difficulty understanding speech experienced the greatest amount of perceived benefit from vibrotactile feedback.

Sleep is critical for the consolidation of recent experiences into long-term memories. As a key underlying neuronal mechanism, hippocampal sharp-wave ripples (SWRs) occurring during sleep define periods of hippocampal reactivation of recent experiences and have been causally linked with memory consolidation. Hippocampal SWR-dependent memory consolidation during sleep is often referred to as occurring during an \"offline\" state, dedicated to processing internally generated neural activity patterns rather than external stimuli. However, the brain is not fully disconnected from the environment during sleep. In particular, sounds heard during sleep are processed by a highly active auditory system which projects to brain regions in the medial temporal lobe, reflecting an anatomical pathway for sound modulation of hippocampal activity. While neural processing of salient sounds during sleep, such as those of a predator or an offspring, is evolutionarily adaptive, whether ongoing processing of environmental sounds during sleep interferes with SWR-dependent memory consolidation remains unknown. To address this question, we used a closed-loop system to deliver non-waking sound stimuli during or following SWRs in sleeping rats. We found that exposure to sounds during sleep suppressed the ripple power and reduced the rate of SWRs. Furthermore, sounds delivered during SWRs (On-SWR) suppressed ripple power significantly more than sounds delivered 2 seconds after SWRs (Off-SWR). Next, we tested the influence of sound presentation during sleep on memory consolidation. To this end, SWR-triggered sounds were applied during sleep sessions following learning of a conditioned place preference paradigm, in which rats learned a place-reward association. We found that On-SWR sound pairing during post-learning sleep induced a complete abolishment of memory retention 24 h following learning, while leaving memory retention immediately following sleep intact. In contrast, Off-SWR pairing weakened memory 24 h following learning as well as immediately following learning. Notably, On-SWR pairing induced a significantly larger impairment in memory 24 h after learning as compared to Off-SWR pairing. Together, these findings suggest that sounds heard during sleep suppress SWRs and memory consolidation, and that the magnitude of these effects are dependent on sound-SWR timing. These results suggest that exposure to environmental sounds during sleep may pose a risk for memory consolidation processes.

OBJECTIVE: Mental health problems are increasing at an alarming rate, calling for the need for more cost-effective and easily accessible interventions. Visual images and sounds depicting nature have been found to have positive effects on individuals\' mood and well-being; however, the combined effects of images and sounds have been scarcely investigated. This study therefore aimed to compare the mood effects of viewing nature-related soothing images versus listening to soothing sounds versus a combination of both.
METHODS: In this study, 149 participants aged 18-83 years old (M = 35.88, SD = 15.63; 72.5% female, male 26.8%, .7% transgender) were randomised into three intervention conditions: images only, sounds only or combined (images and sounds). Baseline depressive and anxiety symptoms were indexed, and four outcome variables (positive affect, negative affect, serenity affect and depressive mood states) were measured pre- and post-intervention.
RESULTS: Findings showed that all participants, regardless of group, reported a decrease in negative affect, positive affect and depressive mood as well as an increase in serenity affect (including feelings of soothe). However, there were no group differences. Exploratory analyses found that individuals with higher levels of depressive and anxiety symptoms at baseline experienced greater reduction in negative affect and depressive mood state, as well as a larger increase in serenity affect.
CONCLUSIONS: These findings therefore provide preliminary evidence that, upon further research and development, images and sounds depicting nature can potentially be developed for use as an effective tool to improve mood and well-being.

Interpretation of breath sounds by auscultation has high inter-observer variability, even when performed by trained healthcare professionals. This can be mitigated by using Artificial Intelligence (AI) acoustic analysis. We aimed to develop and validate a novel breath sounds analysis system using AI-enabled algorithms to accurately interpret breath sounds in children. Subjects from the respiratory clinics and wards were auscultated by two independent respiratory paediatricians blinded to their clinical diagnosis. A novel device consisting of a stethoscope head connected to a smart phone recorded the breath sounds. The audio files were categorised into single label (normal, wheeze and crackles) or multi-label sounds. Together with commercially available breath sounds, an AI classifier was trained using machine learning. Unique features were identified to distinguish the breath sounds. Single label breath sound samples were used to validate the finalised Support Vector Machine classifier. Breath sound samples (73 single label, 20 multi-label) were collected from 93 children (mean age [SD] = 5.40 [4.07] years). Inter-rater concordance was observed in 81 (87.1%) samples. Performance of the classifier on the 73 single label breath sounds demonstrated 91% sensitivity and 95% specificity. The AI classifier developed could identify normal breath sounds, crackles and wheeze in children with high accuracy.

Would you get close to a stinky perfume bottle or to a loudspeaker producing noise? In this paper, we present two procedures that allowed us to assess the ability of auditory and olfactory cues to elicit automatic approach/avoidance reactions toward their sources. The procedures resulted from an adaptation of the Visual Approach/Avoidance by the Self Task (VAAST; Rougier et al., 2018), a task having the peculiarity of simulating approach/avoidance reactions by using visual feedback coming from the whole-body movements. In the auditory VAAST (Experiment 1), participants were instructed to move forward or backward from a loudspeaker that produced spoken words differentiated by their level of distortion and thus by their hedonic value. In the olfactory VAAST (Experiment 2), participants were asked to move forward or backward from a perfume bottle that delivered pleasant and unpleasant odors. We expected, consistent with the approach/avoidance compatibility effect, shorter latencies for approaching positive stimuli and avoiding negative stimuli. In both experiments, we found an effect of the quality of the emotional stimulus on forward actions of participants, with undistorted words and pleasant odors inducing faster forward movements compared with that for distorted words and unpleasant odors. Notably, our results further suggest that the VAAST can successfully be used with implicit instructions, i.e., without requiring participants to explicitly process the valence of the emotional stimulus (in Experiment 1) or even the emotional stimulus itself (in Experiment 2). The sensitivity of our procedures is analyzed and its potential in cross-modal and (contextualized) consumer research discussed.