Voice Research Articles

Behavioral addictions and psychosis

M.K* is a 27-year-old, single, unemployed male that was driven to the Emergency Department by his foster father, four weeks ago with first episode of psychiatric symptoms of tactile hallucinations, auditory hallucinations of male and female voices making inappropriate sexual comments about him, persecutory delusions and delusions of control for the past five days. M.K is a daily cannabis user of 0.5-1g use for the past 2 years and has 5.5 pack year smoking history. M.K also reports having a pornography and masturbation addiction for 2 years with marked intrusive thoughts of sexual nature the past week. M.K has no medical or psychiatric history. Recent stressor was moving out of foster father’s house 8 days ago. The symptoms led to significant impact at work which he has quit since then. On presentation, M. K showed partial insight into his third person running commentary hallucinations but believed adamantly that he was being watched, followed and controlled. He reported hearing his female neighbour stating that he has sexual interest in animals and later heard his manager making pedophilic allegations on him. M.K was so distressed, he quit work and isolated himself in his room. He reported poor concentration and lack of appetite for the past week. M.K describes his baseline mood to have “always been not the greatest” and denied anhedonia, fatigue, or sleep changes. He denied thoughts of self- harm, harm to others or suicidal ideation. Four weeks following inpatient, referral to HBCT and cannabis abstinence has shown improvement in psychiatric symptoms with absence of hallucinations, however, there has been increased symptoms of anxiety with “panic attacks”. M.K’s biological mother is reported to have history of substance misuse and sister with depressive symptoms. He continues to withdraw from society with increased time spent indoors gaming and shows emotional dependence on foster father.

Enhancing Acoustic Data Mobilization: A User-Friendly Data Platform for the Asian Soundscape Monitoring Network

Passive Acoustic Monitoring (PAM) has emerged as a crucial tool in monitoring efforts to track environmental changes and evaluate conservation measures in response to the biodiversity crisis (Sugai et al. 2018). PAM now offers long-term and continuous insights into biodiversity, using acoustic indices correlating with biodiversity and deep-learning tools to aid in the detection and identification of animal sounds (Sueur et al. 2014, Kahl et al. 2021, Wu et al. 2022). However, managing and mobilizing original recordings remains challenging due to their large size and lack of structure, hindering broader applications of these valuable data. Established in 2014 by Academia Sinica and Taiwan Forestry Research Institute, the Asian Soundscape Monitoring Network has amassed over 20 million minutes of audible and ultrasonic recordings from diverse landscapes, including forests, wetlands, urban parks and farmlands across Malaysia, Thailand, Taiwan and Vietnam. To enhance data mobilization and utilization, we developed a user-friendly data platform enabling browsing, searching, visualization, exploration and retrieval of the original recordings (Fig. 1), as well as derived data such as acoustic indices and species occurrences, and associated weather records (Fig. 2) The platform also allows users to visualize the temporal dynamics of the soundscape and identify acoustic events at monitoring sites by examining long-term spectrograms and time series of acoustic indices (Fig. 3). Detailed information about the monitoring sites and recorder deployment is provided. Each recording is tagged with a Creative Commons license, and a unique Archival Resource Key is assigned to every data retrieval for persistent identification, facilitating data reuse. Additionally, recordings containing human voices are identified and restricted to protect privacy. Our aim with this data platform is to streamline the mobilization of acoustic data, foster diverse applications, and enhance the overall value of the data.

Musical Play and Playworlds Create Meaning in Swedish School-Age Educare Centres: A Matter of Engagement, Empathy, Exploration and Embodiment

One of the tasks of Swedish school-age educare centres is to offer children the possibility of different aesthetic forms of expression, such as music and drama. Based on theories of play, music and improvisation, musical play is introduced in which the process itself and the desire to participate are in focus, with the intention of investigating children’s and teachers’ joint meaning-making during the sound exploration and creation of playworlds. From a staged action-focused method, joint play with different voice sounds, both in song and speech, is introduced along with sounds and rhythms from everyday things, such as plastic bags and chopsticks. During the musical play, a fictional character is introduced to create possible openings for voluntary participation and engagement. The results are presented in four scenes and focus on engagement, empathy, exploration, and embodiment. In the results, the participants’ meaning-making is described as action during the musical play and the creation of the playworld. This study is expected to generate a basis for the discussion on joint musical play and play pedagogy as a form of extended education pedagogy capable of creating an experience of emancipation and participation in encounters between children and teachers.

How Does Talking with a Human-like Machine in a Self-Driving Car Affect your Experience? A Mixed-Method Approach

This study investigates the impact of human-like machines (HLMs) on the user experience (UX) of young adults during voice interactions between drivers and autonomous vehicles. A mixed-method approach was employed to evaluate three voice agents with varying levels of anthropomorphism: a machine voice without humanized speech strategies (Agent A), a human voice without humanized speech strategies (Agent B), and a human voice with humanized speech strategies (Agent C). A total of 30 participants were invited to interact with the agents in a simulated driving scenario. Quantitative measures were employed to assess intimacy, trust, intention to use, perceived safety, and perceived anthropomorphism based on a 7-point Likert scale, while qualitative interviews were conducted to gain deeper insights. The results demonstrate that increased anthropomorphism enhances perceived anthropomorphism (from 2.77 for Agent A to 5.01 for Agent C) and intimacy (from 2.47 for Agent A to 4.52 for Agent C) but does not significantly affect trust or perceived safety. The intention to use was higher for Agents A and C (4.56 and 4.43, respectively) in comparison to Agent B (3.88). This suggests that there is a complex relationship between voice characteristics and UX dimensions. The findings of this study highlight the importance of balancing emotional engagement and functional efficiency in the design of voice agents for autonomous vehicles.

Mapping human voice in urban spaces

Human voice plays a pivotal role as a sound source in urban environments. Despite the plethora of natural sound sources present in urban spaces, human voice often stands out as one of the sound source, exerting a significant influence on the perception and affection of these spaces. However, compared to other aspects of urban soundscapes, such as traffic noise (air, road, rail), human voice cartography and modelling remains relatively underexplored, with limited historical development and scholarly attention. This research gap led to the deployment of an experimental protocol in Nantes, France, to produce a comprehensive voice sound map and compare it to perceptual data. This protocol involved the collection of sound level measurements during two distinct measurement campaigns using the NoiseCapture smartphone application, coupled with surveys capturing perceptual information such as the circumplex circle of affect, perceived presence of sound sources, emergence of sound sources, and variability of the sound environment. Additionally, sound environment simulations were conducted using NoiseModelling. The present paper shows the method used to evaluate the audibility of human speech in urban spaces. During the presentation, comparisons with perceptual measurements will be presented.

Investigating the after effect of head-tracked movement on externalization for varying sound sources in binaural synthesis.

Binaural audio reproduction aims to create a realistic auditory experience for the listener through headphones. However, front and rear sound sources are often internalized (perceived inside the head) rather than externalized (perceived outside the head). Previous studies have shown that large head movements can significantly improve externalization, and that this improvement can persist even after head movements have stopped. This study examined how head-tracked movements influence the perception of sound externalization depending on the nature of the sound sources. The stimuli consisted of a first ``head movement" part during which the participants had to either perform a head movement or stay still, followed by a "rating" part where they evaluated externalization without moving. The sound sources during the ``rating" part could be similar, slightly different, or very different from the source during the head movement part. Results demonstrated that head-tracked movements effectively heightened externalization perception for all types of sources immediately after the movement. The type of source (female voice, male voice, or pink noise) did not affect perceived externalization. These findings suggest that the externalization enhancement induced by head-tracked movement persists after the movement ends even when encountering a different sound source.

The Role of Name, Origin, and Voice Accent in a Robot's Ethnic Identity.

This paper presents the results of an experiment that was designed to explore whether users assigned an ethnic identity to the Misty II robot based on the robot's voice accent, place of origin, and given name. To explore this topic a 2 × 3 within subject study was run which consisted of a humanoid robot speaking with a male or female gendered voice and using three different voice accents (Chinese, American, Mexican). Using participants who identified as American, the results indicated that users were able to identify the gender and ethnic identity of the Misty II robot with a high degree of accuracy based on a minimum set of social cues. However, the version of Misty II presenting with an American ethnicity was more accurately identified than a robot presenting with cues signaling a Mexican or Chinese ethnicity. Implications of the results for the design of human-robot interfaces are discussed.

Human voice absorbing system by the use of aeroacoustics metamaterials

The increase of calls meetings has intensified vocal noise pollution, particularly in open spaces and during transportation. This poses challenges not only for speakers seeking confidentiality but also for disturbed neighbours. Both workplace and transportation environments suffer from the disruptive nature of vocal noise, with direct implications for cognitive performance in office settings. To answer to that problem, Skyted propose an innovative acoustic mask designed to reduce voice noise by up to 35 dB at a distance of 1 meter. This technology comes from meta-materials initially developed at ONERA for aircraft engine applications. Adapted and modeled for human vocal use, Skyted's mask ensures optimal comfort, breathability, and bidirectional attenuation. The numerical models based on FEM, and analytical (Matrix Transfert based on) are compared to measurements made for those specific application.

Zygosity Effects on Human Voice: Fundamental Frequency Analysis of Brazilian Twins' Speech.

Voice production can be influenced by interindividual variations related to genetic, physiological, behavioral, and several environmental factors. Here we examined the effect of zygosity on speaking fundamental frequency (F0) statistical descriptors. Our aims were: (1) to determine whether the genetic similarity between monozygotic (MZ) and dizygotic (DZ) twins affects F0 characteristics, and (2) to quantify the contribution of genetic factors to these characteristics. The study involved 79 same-sex twin pairs of Brazilian Portuguese speakers, comprising 65 MZ and 14 DZ twins, aged 18 to 66 years (31.7 ± 11.6 years), with 21 male and 58 female pairs. Participants were recorded while uttering a greeting phrase and the Brazilian Portuguese version of the 'Happy Birthday to You' song. Speech segments were analyzed using Praat free software, and F0 measures were automatically extracted in both Hertz and semitone scales. Statistical descriptors, including centrality, dispersion, and extreme values of F0 were examined, and the ACE model (i.e., total genetic effects, A; shared environmental influences, C; and nonshared environmental influences, E) was employed to estimate the additive effect;ts of monozygosity. As anticipated, we observed a zygosity effect on several F0 parameters, with more similarity between MZ twins compared to DZ twins. We discuss the genetic influences on F0 parameters and the absence of a monozygosity effect in two of them. Additionally, we briefly address potential biases associated with the selected measurement scale for statistical modeling. Finally, we explore the influence of genetic factors on F0 patterns, as well as environmental, life history and linguistic factors, particularly concerning F0 variation in speech.

Using the Cocktail Party Effect to Add the Coding Dimension of Auditory Event Related Potential Brain-Computer Interface.

The auditory event-related potential based brain-computer interface (aERP-BCI) is a classical paradigm of brain-computer communication. To improve the coding efficiency of aERP-BCI, this study proposes a method using two parallel voice channels to add the coding dimension based on the cocktail party effect. The novel paradigm used male and female voices to establish two parallel oddball sound stimulus sequences. In comparison, the baseline paradigm only presented male or female stimulus sequences. Both the double voice condition (DVC) and the single voice condition (SVC) paradigms carried out offline experiments and the DVC also carried out online experiment. Subsequently, the EEG signal and BCI operation results were compared and analyzed. The cocktail party effect caused a significant difference in the EEG responses of non-target stimulus between the focused vocal channel and the ignored vocal channel under the DVC paradigm, and the focused and ignored channels achieved a recognition accuracy of 97.2%. The target recognition rate of DVC was 82.3%, with no significant difference compared with 85% of SVC while the information transfer rate (ITR) of DVC reaching 15.3 bits/min was significantly higher than that of SVC. The cocktail party effect improves the coding efficiency by adding parallel channels without reducing the target/non-target stimulus recognition in the focused vocal channel. This provides a novel direction for the performance improvement of aERP-BCI.

A Self‐Powered, Highly Sensitive, and Frequency‐Tunable Triboelectric Acoustic Sensor Inspired by the Human Cochlea

AbstractConventional acoustic sensors used in human–machine interfaces often face challenges such as power supply requirements, limited sensitivity, and inability to tune their frequency response. A self‐powered, highly sensitive, and frequency‐tunable triboelectric acoustic sensor inspired by the human cochlea is introduced. By mimicking hair cells in the organ of Corti, a tapered microhair‐structured ferroelectric poly(vinylidene fluoride‐co‐hexafluoropropylene) (PVDF‐HFP) and barium titanate nanoparticle (BTNP) composite film is proposed, which demonstrates a 16‐fold increase in triboelectric output voltage (1.3 V) compared to a planar one at 2.8 Pa. Furthermore, inspired by the frequency selectivity of the basilar membrane with gradient structural variations, integrating a mass‐beam diaphragm is proposed with varying kirigami length and circular mass diameter that enables precise tuning of the resonance frequency of the sensor, resulting in a 32 times improvement in sensitivity (860 mV Pa−1) compared to a nonbiomimetic sensor (28 mV Pa−1) and an expanded dynamic range. The proposed sensor differentiates between human voices with different frequencies. A robotic hand integrated with the sensor responds to acoustic stimuli with programmed hand gestures, which highlights its potential in acoustic human–machine interfaces. The biomimetic approach to developing a self‐powered, highly sensitive, and frequency‐tunable acoustic sensor offers new possibilities for intuitive and immersive human–machine interfaces.

Xeinabot: A Spoken Intelligent Agent approach Using Hidden Markov Model with Chatbot Technology in Android Environmen

The present study describes the designing and its execution of xeinabot, a public domains spoken smart agent in an Android system. The primary goal of this work is to design and construct a personal agent that combines chatbot technology and statistical methods for speech search. The former uses Hidden Markove System Algorithmic procedures and the N-gram technique for Automatically Speech Recognition, while the latter relies on chatbot systems for Speech Recognizing and uses Multinomial Naïve Bays Method for classification and brute force search for matching patterns. The main objective of this strategy is to create an agent that convinces people into thinking they are speaking with a human when, in reality, they are speaking with a machine. utilizing chatbot technology to make advantage. After evaluating roughly 500 phrases on various subjects, the evaluation findings show very good results and, in the majority of circumstances, the agent behaves like a person. The success task (correct voice recognition and speech understanding) amounts to 86.6%.

Xeinabot: A Spoken Intelligent Agent approach Using Hidden Markov Model with Chatbot Technology in Android Environmen

The present study describes the designing and its execution of xeinabot, a public domains spoken smart agent in an Android system. The primary goal of this work is to design and construct a personal agent that combines chatbot technology and statistical methods for speech search. The former uses Hidden Markove System Algorithmic procedures and the N-gram technique for Automatically Speech Recognition, while the latter relies on chatbot systems for Speech Recognizing and uses Multinomial Naïve Bays Method for classification and brute force search for matching patterns. The main objective of this strategy is to create an agent that convinces people into thinking they are speaking with a human when, in reality, they are speaking with a machine. utilizing chatbot technology to make advantage. After evaluating roughly 500 phrases on various subjects, the evaluation findings show very good results and, in the majority of circumstances, the agent behaves like a person. The success task (correct voice recognition and speech understanding) amounts to 86.6%.

Neurophysiological Assessment in Children with Vocal Fold Paralysis: A Tertiary Center Experience.

The aim of this study is to report on experience acquired during the laryngeal electrophysiological assessment with Co-MEP and L-EMG in pediatric patients with acquired, congenital, and syndromic vocal fold paralysis (VFP), and correlate our findings with patients' characteristics, their comorbidities, and VFP etiology. Pediatric patients with suspected or previously diagnosed unilateral or bilateral VFP underwent electrophysiological records under general anesthesia; corticobulbar motor-evoked potentials (Co-MEPs) and laryngeal electromyography (L-EMG) of thyroarytenoid (TA) and posterior cricoarytenoid (PCA) muscles were recorded. Statistical analysis revealed a statistically significant correlation between early gestational age at childbirth and TA muscle intensity (p = 0.002) and PCA muscle intensity (p = 0.002); tracheostomy presence and TA muscle intensity (p = 0.002) and PCA muscle intensity (p = 0.002); presence of genetic anomalies with intensity and latency for TA muscle and latency for PCA muscle (TA latency p = 0.015, TA intensity p = 0.021, PCA latency p = 0.035); congenital presentation of VFP and an increased intensity for TA muscle (p = 0.04); latency and intensity for TA muscle (p = 0.024); TA muscle intensity and PCA intensity (p = 0.005). Intraoperative Co-MEPs and L-EMG are two complementary tools for evaluating the functional integrity of the structures involved in conveying signals from the motor cortex to TA and PCA muscles in children with vocal fold paralysis. Further studies are needed to establish their ability to predict the recovery of VF mobility, which could potentially lead to decannulation. Level 4 Laryngoscope, 2024.

Phoneme Recognition in Korean Singing Voices Using Self-Supervised English Speech Representations

In general, it is difficult to obtain a huge, labeled dataset for deep learning-based phoneme recognition in singing voices. Studying singing voices also offers inherent challenges, compared to speech, because of the distinct variations in pitch, duration, and intensity. This paper proposes a detouring method to overcome this insufficient dataset, and applies it to the recognition of Korean phonemes in singing voices. The method started with pre-training the HuBERT, a self-supervised speech representation model, on a large-scale English corpus. The model was then adapted to the Korean speech domain with a relatively small-scale Korean corpus, in which the Korean phonemes were interpreted as similar English ones. Finally, the speech-adapted model was again trained with a tiny-scale Korean singing voice corpus for speech–singing adaptation. In the final adaptation, melodic supervision was chosen, which utilizes pitch information to improve the performance. For evaluation, the performance on multi-level error rates based on Word Error Rate (WER) was taken. Using the HuBERT-based transfer learning for adaptation improved the phoneme-level error rate of Korean speech by as much as 31.19%. Again, on singing voices by melodic supervision, it improved the rate by 0.55%. The significant improvement in speech recognition underscores the considerable potential of a model equipped with general human voice representations captured from the English corpus that can improve phoneme recognition on less target speech data. Moreover, the musical variation in singing voices is beneficial for phoneme recognition in singing voices. The proposed method could be applied to the phoneme recognition of other languages that have less speech and singing voice corpora.

Development and content validation of coordinate response measure (CRM) corpus in Kannada for informational masking measurement

BackgroundAssessing informational masking (IM) involves various methods, broadly categorized as electrophysiological and behavioral approaches. In behavioral methods, researchers often use a range of stimulus types such as tone-in-noise masking, speech masking, music masking, gap detection, modulation masking, and spatial masking. The evaluation of speech perception in noisy conditions often utilizes the coordinate response measure (CRM), a publicly available test developed by Moore (AGARD conference proceedings 311, 1981). The objective of the study is to develop and content validate the Kannada coordinate response measure (CRM) sentences corpus for the information masking measurement.ResultsStage 1: A total of thirty-eight call signs, eight colors, and eight numbers in the Kannada language were compiled and were given to 15 experts to select the appropriate stimuli. Those stimuli that satisfied the criteria of CVI ≥ 0.90 and CVR ≥ .90 were selected, which consisted of eight call signs, seven numbers, and five colors. Stage 2: By incorporating the chosen call signs, numbers, and colors, seven sentence structures were formulated and were subjected to content validation (criteria of CVI ≥ 0.90 and CVR ≥ .90). The sentence structure “(Call sign) iga (Color) bannada (Number) torsu” was finalized.Stage 3: Eight speakers (four males and four females) recorded Kannada sentences of about 3.5 s each, which were evaluated by five audiologists for voice quality, rate, and speech clarity using a 4-point scale. The evaluation identified two male and two female speakers with the best recordings.Stage 4: The final stage involved recording 235 sentences by the selected speakers, which were then assessed by two Kannada-speaking audiologists for face validity on various parameters, ensuring linguistic appropriateness and cultural relevance for inclusion in the final CRM corpus.ConclusionThe resulting corpus, meticulously curated and content-validated, presents significant potential for advancing research and clinical assessment of informational masking within the Kannada-speaking community. Overall, the CRM’s exceptional performance in challenging listening environments, inherent adaptability across languages, versatility for different age and literacy levels, and effectiveness in speech-intelligibility testing with multiple simultaneous talkers due to its use of call signs underscores its value as a superior measurement tool, which can be used in IM measurement in Kannada-speaking population.

Music source feature extraction based on improved attention mechanism and phase feature

Music source feature extraction is an important research direction in music information retrieval and music recommendation system. To extract the features of music sources more effectively, the study introduces the jump attention mechanism and combines it with the convolutional attention module. Also, a feature extraction module based on Unet + + and spatial attention module is proposed. In addition, the phase feature information of the mixed music signals is utilized to improve the network performance. Results showed that this model was studied to perform well in music source separation experiments of vocals and accompaniment. For vocal separation on the MIR-1K dataset, the model achieves 11.25 dB, 17.34 dB, and 13.83 dB for each metric, respectively. Meanwhile, for drum separation on the DSD100 dataset, the model achieves a median signal-to-source distortion ratio of 4.36 dB, which is 2.91 dB better than that of the Spectral Hierarchical Network model. For the separation of the bass sound and the human voice, the model's in the separation of bass and human voice, the median distortion ratio of the model is as high as 4.87 dB and 6.09 dB, which is better than that of the Spectral Hierarchical Network model. This indicates the significant performance advantages in feature extraction and separation of music sources, and it has important application values in music production and speech recognition.

A Nanoparticle-Based Artificial Ear for Personalized Classification of Emotions in the Human Voice Using Deep Learning.

Artificial intelligence and human-computer interaction advances demand bioinspired sensing modalities capable of comprehending human affective states and speech. However, endowing skin-like interfaces with such intricate perception abilities remains challenging. Here, we have developed a flexible piezoresistive artificial ear (AE) sensor based on gold nanoparticles, which can convert sound signals into electrical signals through changes in resistance. By testing the sensor's performance at both frequency and sound pressure level (SPL), the AE has a frequency response range of 20 Hz to 12 kHz and can sense sound signals from up to 5 m away at a frequency of 1 kHz and an SPL of 126 dB. Furthermore, through deep learning, the device achieves up to 96.9% and 95.0% accuracy in classification and recognition applications for seven emotional and eight urban environmental noises, respectively. Hence, on one hand, our device can monitor the patient's emotional state by their speech, such as sudden yelling and screaming, which can help healthcare workers understand patients' condition in time. On the other hand, the device could also be used for real-time monitoring of noise levels in aircraft, ships, factories, and other high-decibel equipment and environments.

Doubly disenfranchised: the experience of paternal grief following medical termination in Jérémie Szpirglas’ Pater dolorosa

ABSTRACT The term ‘disenfranchised grief’ is increasingly being used to designate grief experiences that are overlooked by wider society. In the French context, this term has overwhelmingly been applied to perinatal loss. Focusing on medical termination (IMG), a somewhat liminal category of perinatal loss, this article considers the doubly disenfranchised experience of paternal grief in such circumstances. While IMG-related grief is, in itself, disenfranchised, not least because it lacks societal recognition, paternal grief following IMG is doubly so, since the male voice is seldom heard. Taking as its focus Pater dolorosa (2019), author and journalist Jérémie Szpirglas’ narrative of medical termination, this article will consider the value of the term ‘disenfranchised grief’ in naming the experience of grief to which Szpirglas’ text attests; the capacity of the text to give voice to that experience and to offer a textual transposition of it; and the role of male grief writing following medical termination in beginning to carve out an alternative space for the sharing of a grief experience that defies established social norms. The article will therefore suggest, in line with Rita Felski’s argument, that ‘a literary text could know as much, or more, than a theory’, particularly when it comes to individual experiences of grief.

An Exploratory Analysis of ChatGPT Compared to Human Performance With the Anesthesiology Oral Board Examination: Initial Insights and Implications.

Chat Generative Pre-Trained Transformer (ChatGPT) has been tested and has passed various high-level examinations. However, it has not been tested on an examination such as the American Board of Anesthesiology (ABA) Standardized Oral Examination (SOE). The SOE is designed to assess higher-level competencies, such as judgment, organization, adaptability to unexpected clinical changes, and presentation of information. Four anesthesiology fellows were examined on 2 sample ABA SOEs. Their answers were compared to those produced by the same questions asked to ChatGPT. All human and ChatGPT responses were transcribed, randomized by module, and then reproduced as complete examinations, using a commercially available software-based human voice replicator. Eight ABA applied examiners listened to and scored the topic and modules from 1 of the 4 versions of each of the 2 sample examinations. The ABA did not provide any support or collaboration with any authors. The anesthesiology fellow's answers were found to have a better median score than ChatGPT, for the module topics scores (P = .03). However, there was no significant difference in the median overall global module scores between the human and ChatGPT responses (P = .17). The examiners were able to identify the ChatGPT-generated answers for 23 of 24 modules (95.83%), with only 1 ChatGPT response perceived as from a human. In contrast, the examiners thought the human (fellow) responses were artificial intelligence (AI)-generated in 10 of 24 modules (41.67%). Examiner comments explained that ChatGPT generated relevant content, but were lengthy answers, which at times did not focus on the specific scenario priorities. There were no comments from the examiners regarding Chat GPT fact "hallucinations." ChatGPT generated SOE answers with comparable module ratings to anesthesiology fellows, as graded by 8 ABA oral board examiners. However, the ChatGPT answers were deemed subjectively inferior due to the length of responses and lack of focus. Future curation and training of an AI database, like ChatGPT, could produce answers more in line with ideal ABA SOE answers. This could lead to higher performance and an anesthesiology-specific trained AI useful for training and examination preparation.