Audio Recordings Research Articles

The Resilience and Lived Experiences of the Parents of Children With Autism in India: A Mixed-method Study

Background and Objectives: Families dealing with autism spectrum disorder (ASD) children try to adapt with different strategies. 1) To assess the resilience of parents dealing with children having ASD and its associated factors. 2) To explore the perspective and strategies of families dealing with children having ASD Methods: This was a mixed-methods study done over a period of 3 months among parents having children diagnosed with ASD; undergoing institutional therapy for more than 6 months in duration. Data collection was done using the PREQ questionnaire and key informant interviews (KII). Informed consent was taken prior to each interview and audio recordings. Relevant tests of significance and deductive analysis followed. Results: There was an equal divide observed between the low (50%) and high resilience (50%) groups. Binary logistic regression showed that the upper socio-economic class showed higher odds of better resilience (OR=4.038, 95% CI, 2.857%, 4.894%) as compared to the lower socio-economic class, and those with higher levels of education showed better resilience (OR=9.903, 95% CI, 2.502%, 3.483% than the lesser educated. KII explored different perspectives on personal experiences, concerns, challenges, attitudes, etc. where both perspectives such as benefits and hardships were addressed on an individual as well as a family basis, respectively Conclusion: Education and socio-economic backgrounds played a role in mending the resilience and other active measures such as peer support mechanisms and self-coping strategies also influenced the attitude and improved determination of parents dealing with children having ASD.

A matter of time and space: reflections on the use of chatbots to assist the collection of audio diaries during the COVID-19 pandemic in Brazil

ABSTRACT The use of qualitative audio diaries in research allows people to generate multi-occasion reports of events in their natural, spontaneous contexts in a recorded audio format. Recent technological advances have enabled more rapid, spontaneous means for audio diaries recordings, such as smartphones. This article reports on methodological insights regarding the feasibility and contributions of using chatbots – digital systems that provide an interface for interaction with users that emulate human conversation – to assist the collection of audio diaries. We describe the development of a WhatsApp chatbot for the remote collection and sharing of audio files using a diary format. Methodological considerations are presented, drawing from the results of a remote collection of spoken reports from 19 Brazilian undergraduate students who were experiencing social isolation due to COVID-19 pandemic-related containment measures. Results emphasize the temporal aspect of the data collection process, and indicate that the tool allowed participants to generate accounts depicting changes in their understanding of perceptions and experiences over time. Although leveraging digital technology and conversational-like features of chatbots may promote greater participation and less participant burden, results also suggest that using pre-scripted prompts in the form of open questions may pose a challenge for reflexive engagement with audio diaries.

Mobile App for Patients With Chronic Obstructive Pulmonary Diseases During Home-Based Exercise Care: Usability Study.

Digital health tools have demonstrated promise in the treatment and self-management of chronic diseases while also serving as an important means for reducing the workload of health care professionals (HCPs) and enhancing the quality of care. However, these tools often merely undergo large-scale testing or enter the market without undergoing rigorous user experience analysis in the early stages of their development, leading to frequent instances of low use or failure. This study aims to assess the usability of and satisfaction with a mobile app designed for the clinical monitoring of patients with chronic obstructive pulmonary disease undergoing pulmonary rehabilitation at home. This study used a mixed methods approach involving two key stakeholders-patients with chronic obstructive pulmonary disease and HCPs-across three phases: (1) mobile app mock-up design, (2) usability testing, and (3) satisfaction evaluation. Using convenience sampling, participants were grouped as HCPs (n=12) and patients (n=18). Each received a tablet with mock-ups for usability testing through interviews, with audio recordings transcribed and analyzed anonymously in NVivo12.0, focusing on mock-up features and usability insights. Task difficulty was rated from 1 (very easy) to 5 (very difficult), with noncompletion deemed a critical error. Usability satisfaction was measured on a 5-point Likert scale from 1 (strongly disagree) to 5 (strongly agree). The research indicated a notable difference in app usability perceptions: 66% (8/12) of HCPs found tasks "very easy," compared to only 22% (4/18) of patients. Despite this, no participant made critical errors or withdrew, and satisfaction was high. HCPs completed tasks in about 20 minutes, while patients took 30. Older adults faced challenges with touch screens and scroll menus, suggesting the need for intuitive design aids like auditory support and visual health progress indicators, such as graphs. HCPs noted potential data delays affecting service, while non-native-speaking caregivers faced interpretation challenges. A secure pairing system for privacy in teleconsultations proved difficult for older users; a simpler icon-based system is recommended. This study highlights the need to consider stakeholder abilities in medical app design to enhance function implementation. Most HCPs (11/12, 91%) found the app intuitive, though they recommended adding icons to show patient progress to support clinical decisions. In contrast, 62% (11/18) of patients struggled with tablet navigation, especially with connectivity features. To ensure equitable access, the design should accommodate older users with diverse abilities. Despite challenges, both groups reported high satisfaction, with patients expressing a willingness to learn and recommending the app. These positive usability evaluations suggest that, with design improvements, such apps could see increased use in home-based care.

Child activity contexts and language environments

Abstract Activity contexts are increasingly recognized as important for the variation observed in the type and quantity of speech heard by children. However, there is little data from children’s everyday experiences to properly study this role. We analyzed the quantity of target child-directed speech (TDS) and other-directed speech (ODS) according to children’s activity contexts. We used Daylong Audio Recordings of American English children aged 6–17 months old from the Bergelson Seedlings corpus. A higher quantity of ODS per minute was observed in Solitary playful and exploratory activity contexts, while a higher quantity of TDS per minute was observed in Social activity contexts in comparison to other activity contexts. However, the interindividual variation found needs to be further explored. These results highlight the link between the language environment and activity contexts, and their importance for understanding child language development.

The Pan-African Surgical Healthcare Forum: An African qualitative consensus propagating continental national surgical healthcare policies and plans.

Access to equitable, safe, affordable, timely, and quality surgical healthcare in Africa remains limited. Few African countries have surgical healthcare plans or policies. Where these exist, there are significant gaps in dissemination, funding, and implementation. A Pan-African Surgical Healthcare Forum (PASHeF) was initiated to address this. The inaugural forum was a two-day consensus conference of technocrats from African Ministries of Health hosted by the Honorable Minister for Health of Rwanda in Kigali. Through coordinated discussions, plenary sessions, working groups, and technocrat networking, they charted the path forward for national surgical healthcare policies and plans. Discussions were sparked by country experiences, and working groups focused on curated context-specific, face-validated questions. Documentation involved field notes, audio recordings, and artificial intelligence transcription. Data was coded using a constant comparative method to itemize delegates' observations, declarations, and recommendations, with member checking. A consensus statement was generated using an inclusive decision-making model. Thirty-two Ministries of Health were represented by 42 delegates who drafted and unanimously adopted the PASHeF 2023 Consensus Statement. This was a 50-point consensus addressing country commitment, leadership, financing, stakeholder mobilization, monitoring and evaluation, partnerships, and other aspects of national surgical healthcare planning in Africa. This consensus is the African roadmap and emphasizes implementation, the need for flexibility in policy development, and current opportunities and barriers. It emphasizes that community involvement and sustainability should undergird this planning, in addition to a focus on the entire spectrum of surgical healthcare, including prevention and rehabilitation. Delegates endorsed PASHeF as an annual event with a secretariat and recommended the creation of a Pan-African Surgical Healthcare Policy monitoring system, and that issues of surgical healthcare should be escalated as an agenda item on African Union and sub-regional ministerial meetings. African nations have embraced surgical healthcare policy as an imperative on their journey towards Universal Health Coverage.

The voice of depression: speech features as biomarkers for major depressive disorder.

Psychiatry faces a challenge due to the lack of objective biomarkers, as current assessments are based on subjective evaluations. Automated speech analysis shows promise in detecting symptom severity in depressed patients. This project aimed to identify discriminating speech features between patients with major depressive disorder (MDD) and healthy controls (HCs) by examining associations with symptom severity measures. Forty-four MDD patients from the Psychiatry Department, University Hospital Aachen, Germany and fifty-two HCs were recruited. Participants described positive and negative life events, which were recorded for analysis. The Beck Depression Inventory (BDI-II) and the Hamilton Rating Scale for Depression gauged depression severity. Transcribed audio recordings underwent feature extraction, including acoustics, speech rate, and content. Machine learning models including speech features and neuropsychological assessments, were used to differentiate between the MDD patients and HCs. Acoustic variables such as pitch and loudness differed significantly between the MDD patients and HCs (effect sizes 𝜼2 between 0.183 and 0.3, p < 0.001). Furthermore, variables pertaining to temporality, lexical richness, and speech sentiment displayed moderate to high effect sizes (𝜼2 between 0.062 and 0.143, p < 0.02). A support vector machine (SVM) model based on 10 acoustic features showed a high performance (AUC = 0.93) in differentiating between HCs and patients with MDD, comparable to an SVM based on the BDI-II (AUC = 0.99, p = 0.01). This study identified robust speech features associated with MDD. A machine learning model based on speech features yielded similar results to an established pen-and-paper depression assessment. In the future, these findings may shape voice-based biomarkers, enhancing clinical diagnosis and MDD monitoring.

CMS's Drug Price Negotiation Program 2023 Patient-Focused Listening Sessions: A Descriptive Analysis of Speaker Remarks.

The US Centers for Medicare and Medicaid Services (CMS) held patient-focused listening sessions in Fall 2023 for each of the first ten drugs selected for the Inflation Reduction Act's (IRA) Drug Price Negotiation Program (DPNP). This study aimed to quantitatively describe speaker input at the sessions, including the absolute and relative time allocated to key areas of interest for the DPNP. In this descriptive analysis of speaker remarks from ten CMS-hosted patient-focused listening sessions, speaker demographics were examined using video streams, time-stamped transcripts, public data, contextual clues, validated tools, and visual assessment when necessary. Audio recordings were transcribed using a speech-to-text application programming interface, followed by human review for accuracy. Transcripts included speaker identification and sentence-level timestamping. Two researchers coded each sentence into predefined categories on the basis of CMS's optional discussion topics, DPNP goals, and potential unintended consequences of the IRA: speaker background, evidence about selected drugs or therapeutic alternatives, drug prices, patient access/benefit design, therapeutic advancements, and other. The total and proportion of time spent by category were calculated per speaker. Out of an anticipated 200 speaker slots, 106 total speakers (median per session: 10; range 5-17) and 70 unique speakers participated, most of whom were patients (n = 38, 54.2%), female (n = 40, 57.1%), and below Medicare age (n = 40, 57.1%). The most popular categories discussed included evidence about the selected drug or therapeutic alternatives (median per slot: 36.5% of time; range 0-93.0%) and patient access/benefit design (median per slot: 12.1%; range 0-75.5%). CMS received a median of 12.3 total minutes of evidence about selected drugs or therapeutic alternatives per listening session across all speakers (range per session 3.9-22.6 minutes). The first listening sessions provided an important, but limited, first step toward patient engagement with the DPNP. Speaker demographics suggest the sessions fell short of capturing the voices of diverse and Medicare-representative patient populations. While speakers often focused their time on patient experience and evidence, CMS received less than 15 minutes of patient-focused evidence about therapeutic alternatives for more than half of the drug listening sessions. CMS has indicated its intent to improve upon the design of the patient-focused listening sessions for drugs selected in the second round of the DPNP. Future iterations should prioritize robust, two-way dialogue, transparency surrounding the impact of patient input on CMS's price determination process, and improvements to event logistics and outreach that facilitate the participation of diverse patients and stakeholders.

Navigating power and impoliteness in criminal court discourse

Abstract This study uses an interactional pragmatic approach to examine impoliteness in Turkish High Criminal Court proceedings, offering an alternative perspective compared to the Anglo-American contexts typically explored in legal discourse research. Grounded in (Culpeper, Jonathan. 1996. Towards an anatomy of impoliteness. Journal of Pragmatics 25. 349–367.) impoliteness super strategies, the analysis draws from 45-min audio recordings of seven criminal trials, focusing on impoliteness during the examination-in-chief. The findings reveal a significant register clash, especially from a defendant who deviates from formal legal norms through misalignment, mock impoliteness, threats, and profanity. This disruption challenges courtroom decorum, affects power dynamics, and influences trial progression and interaction, underscoring the complex interplay between institutional authority and individual behavior, which shapes overall (im)politeness in the courtroom.

HOST COUNTRY LANGUAGE ACQUISITION AMONG FIRST-GENERATION YAGLIDERE IMMIGRANTS IN THE USA AND THE MAINTENANCE OF THE TURKISH LANGUAGE IN SUCCESSIVE GENERATIONS VIA SOCIAL NETWORKS

This article investigated the effect of the social networks of Yaglidere Turkish immigrants on language acquisition and the maintenance of heritage languages by successive generations in the USA. The study was conducted in the cities of Patterson and Burlington between January 2018 and July 2018. This research used qualitative research methods to analyze ethnographic interviews and participant observations. Data were collected using participant observation and informal talks with immigrants conducted in different informal settings such as participants’ houses, their restaurants, and other cafes in Burlington and Paterson. The interviews lasted from 40 to 90 minutes. Questions were open-ended and focused on the role of social networks in the acquisition of English language skills. In order to analyze the resulting data, the audio recordings were transcribed and translated into English. The interviews were first transcribed into Microsoft Word files and then imported into Maxqda, a software program for qualitative analysis, where the data were coded for study. The results indicated that even though social networks have destructive effects among first-generation immigrants, they have undeniable constructive effects on language maintenance in other generations. So, what is destructive for the first generation turns into constructive for the other generations.

Networked microcontrollers for accessible, distributed spatial audio

State-of-the-art systems for spatial and immersive audio are typically very costly, being reliant on specialist audio hardware capable of performing computationally intensive signal processing and delivering output to many tens, if not hundreds, of loudspeakers. Centralised systems of this sort suffer from limited accessibility due to their inflexibility and expense. Building on the research of the past few decades in the transmission of audio data over computer networks, and the emergence in recent years of increasingly capable, low-cost microcontroller-based development platforms with support for both networking and audio functionality, we present a prototype decentralised, modular alternative. Having previously explored the feasibility of running a microcontroller device as a networked audio client, here we describe the development of a client-server system with improved scalability via multicast data transmission. The system operates on ubiquitous, commonplace computing and networking equipment, with a view to it being a simple, versatile, and highly-accessible platform, capable of granting users the freedom to explore audio spatialisation approaches at vastly reduced expense. Though faced by significant technical challenges, particularly with regard to maintaining synchronicity between distributed audio processors, the system produces perceptually plausible results. Findings are commensurate with a capability, with further development and research, to disrupt and democratise the fields of spatial and immersive audio.

CESARAE: computationally efficient and statistical attack resistant audio encryption system

CESARAE: computationally efficient and statistical attack resistant audio encryption system

Evaluating the User Experience and Usability of the MINI Robot for Elderly Adults with Mild Dementia and Mild Cognitive Impairment: Insights and Recommendations

Introduction: In recent years, the integration of robotic systems into various aspects of daily life has become increasingly common. As these technologies continue to advance, ensuring user-friendly interfaces and seamless interactions becomes more essential. For social robots to genuinely provide lasting value to humans, a favourable user experience (UX) emerges as an essential prerequisite. This article aimed to evaluate the usability of the MINI robot, highlighting its strengths and areas for improvement based on user feedback and performance. Materials and Methods: In a controlled lab setting, a mixed-method qualitative study was conducted with ten individuals aged 65 and above diagnosed with mild dementia (MD) and mild cognitive impairment (MCI). Participants engaged in individual MINI robot interaction sessions, completing cognitive tasks as per written instructions. Video and audio recordings documented interactions, while post-session System Usability Scale (SUS) questionnaires quantified usability perception. Ethical guidelines were followed, ensuring informed consent, and the data underwent qualitative and quantitative analyses, contributing insights into the MINI robot’s usability for this demographic. Results: The study addresses the ongoing challenges that tasks present, especially for MD individuals, emphasizing the importance of user support. Most tasks require both verbal and physical interactions, indicating that MD individuals face challenges when switching response methods within subtasks. These complexities originate from the selection and use of response methods, including difficulties with voice recognition, tablet touch, and tactile sensors. These challenges persist across tasks, with individuals with MD struggling to comprehend task instructions and provide correct answers and individuals with MCI struggling to use response devices, often due to the limitations of the robot’s speech recognition. Technical shortcomings have been identified. The results of the SUS indicate positive perceptions, although there are lower ratings for instructor assistance and pre-use learning. The average SUS score of 68.3 places device usability in the “good” category. Conclusions: Our study examines the usability of the MINI robot, revealing strengths in quick learning, simple system and operation, and integration of features, while also highlighting areas for improvement. Careful design and modifications are essential for meaningful engagement with people with dementia. The robot could better benefit people with MD and MCI if clear, detailed instructions and instructor assistance were available.

EcoSound-web: an open-source, online platform for ecoacoustics.

Passive acoustic monitoring of soundscapes and biodiversity produces vast amounts of audio recordings, but the management and analyses of these raw data present technical challenges. A multitude of software solutions exist, but none can fulfil all purposes required for the management, processing, navigation, and analysis of acoustic data. The field of ecoacoustics needs a software tool that is free, evolving, and accessible. We take a step in that direction and present ecoSound-web: an open-source, online platform for ecoacoustics designed and built by ecologists and software engineers. ecoSound-web can be used for storing, re-sampling, organising, analysing, and sharing soundscape recording or metadata projects. Specifically, it allows manual annotation of soniferous animals and soundscape components, automatic annotation with deep-learning models for all birds and for UK bat species, peer-reviewing annotations, analysing audio in time and frequency dimensions, computing alpha acoustic indices, and providing reference sound libraries for different taxa. We present ecoSound-web's structure and features, and describe its operation for typical use cases such as sampling bird and bat communities, using a primate call library, and the analysis of soundscape components and acoustic indices. ecoSound-web is available from: https://github.com/ecomontec/ecoSound-web.

A mixed methods study of student pharmacist perceptions of their confidence and competence in the provision of clinical assessment

Abstract Introduction Pharmacist involvement in clinical assessment or examination has recently come into the focus in the United Kingdom with the transition of the pharmacy workforce to prescribers. Clinical assessment starts with the collection of information on an individual’s past medical history and clinical presentation, and the interpretation of tests, observations, and physical assessments to inform a differential diagnosis.1 The range of clinical skills student pharmacists gain from placements during the MPharm is variable and shaped by local demands for pharmacy services. Therefore, there is a need for additional training on clinical assessment skills in classroom teaching.2-4 Aim To identify student pharmacist perceptions and beliefs on their competence in conducting clinical assessment. Methods Ethics approval for this research study was granted by the Strathclyde Institute of Pharmacy and Biomedical Sciences Ethics Committee and conducted between October-December 2023. A mixed-methods study was conducted using a survey and focus group discussions developed from the literature and validated through discussion to collect student pharmacist perceptions of the role of the pharmacist and current gaps/barriers to pharmacist provision of clinical assessments. Students from all years of the MPharm were invited by email to participate (n=615). Audio recordings captured from focus group discussions were thematically analysed to identify key themes. Results Four focus groups were held with a total of 30 students. There were 89 respondents to the online survey (119 in total). Across both approaches, five key themes were identified from the survey and four from the focus group interviews. These themes centred around student pharmacist perceived role of the pharmacist, time and technical resources available in the pharmacy workplace, and the current curriculum. Most students agreed that such clinics would be beneficial to their training. Discussion and Conclusions Student-led clinics are gaining popularity as a work-based approach to learning. We found varied perceptions of the pharmacist’s role by participant response, suggesting that the clinical nature of pharmacy as a profession must be highlighted to prospective students to ensure those entering the profession are aware of the responsibilities they may be required to undertake. A limitation of this study is that student perceptions reflect the views of a single institution. Careful design of future clinics is required to ensure their seamless integration in the existing MPharm curriculum, in a realistic setting reflecting the workplace, and sufficient support from practitioners to implement them. Future work in this area should focus on how clinical assessment skills should be learned and assessed in student populations.

Contemporary post-Soviet popular music: Politics and aesthetics

Popular music is produced, listened to and distributed all over the world. While there is no doubt that popular music studies, as well as popular music histories and the commercial popular music industry is predominantly Anglophone, popular music is not. This might seem like an obvious statement but looking at current discussions in the field of popular music studies it is a statement that needs to be made again. While there are exceptions, popular music studies in general have a problem with pseudo-universalism. As if the Western English-speaking mainstream reflected ‘popular music’ as a whole. This special issue of IASPM Journal focuses on popular music in the post-Soviet space, imagined as located between Central and Eastern Europe and Central Asia, but also all over the world in reproduction of sounds and the diaspora. The contributions challenge the Anglophone centre of popular music studies.

A Qualitative Inquiry Into Metacognitive Strategies of Postgraduate Students in Employing ChatGPT for English Academic Writing

ABSTRACTRecent years have witnessed a growing application of generative artificial intelligence (GenAI) technology in writing instruction. Students should mobilise their metacognitive strategies during this endeavour to maximise the benefits of GenAI while avoiding the potential negative impacts. Within the context of tertiary education in Hong Kong, this qualitative research investigates 13 postgraduate students' metacognitive strategies when utilising ChatGPT for English academic writing. Using data collected from audio recordings, semi‐structured interviews and human–GenAI chat logs, we explored students' metacognitive strategies within five dimensions, namely, planning, monitoring, evaluating, information management and debugging. The identified themes and subthemes within each dimension exhibited similarities to those observed in other educational settings. Meanwhile, certain metacognitive strategies (e.g., debugging) were found to be unique to the context of GenAI‐supported academic writing. This study contributes to the literature in two ways. Firstly, it provides a detailed and thorough understanding of metacognitive strategies, complementing the extensive quantitative research in this area. Secondly, this research expands the framework of metacognitive strategies to the context of GenAI‐supported academic writing learning.

Biomechanical and machine learning approaches to automating the identification of musical styles and emotions through human motion analysis

This study explores the intricate relationship between biomechanical movements and musical expression, focusing on the identification of musical styles and emotions. Violin performance is characterized by complex interactions between physical actions—such as bowing techniques, finger placements, and posture—and the resulting acoustic output. Recent advances in motion capture technology and sound analysis have enabled a more objective examination of these processes. However, the current literature frequently addresses biomechanics and acoustic features in isolation, lacking an integrated understanding of how physical movements translate into specific musical expressions. Machine Learning (ML), particularly Long Short-Term Memory (LSTM) networks, provides a promising avenue for bridging this gap. LSTM models are adept at capturing temporal dependencies in sequential data, making them suitable for analyzing the dynamic nature of violin performance. In this work, they have proposed a comprehensive model that combines biomechanical analysis with Mel-spectrogram-based LSTM modeling to automate the identification of musical styles and emotions in violin performances. Using motion capture systems, Inertial Measurement Units (IMUs), and high-fidelity audio recordings, we collected synchronized biomechanical and acoustic data from violinists performing various musical excerpts. The LSTM model was trained on this dataset to learn the intricate connections between physical movements and the acoustic features of each performance. Key findings from the study demonstrate the effectiveness of this integrated approach. The LSTM model achieved a validation accuracy of 92.5% in classifying musical styles and emotions, with precision, recall, and F1-score reaching 94.3%, 92.6%, and 93.4%, respectively, by the 100th epoch. The analysis also revealed strong correlations between specific biomechanical parameters, such as shoulder joint angle and bowing velocity, and acoustic features, like sound intensity and vibrato amplitude.

The use of Language ENvironment Analysis in autism research: A systematic review.

In research, language ability has historically been measured using structured tasks in laboratory settings. In recent years, there has been a growing emphasis on the need to instead capture language ability in an individual's natural setting (i.e. through social interaction or in their home). Considering natural language may be particularly important for the autistic population, as an autistic child's language ability can be very different depending on the setting. One common tool for capturing natural language is the LENA recording system, which takes audio recordings over long periods of time and provides estimates of children's and caregivers' speech. The purpose of this systematic review is to summarize the use of LENA in autism research, to highlight the strengths and limitations of the system as identified by researchers, and to provide recommendations for future research and clinical use. We identified 42 autism studies that used LENA in a variety of ways and settings. Most studies used LENA within the guidelines put forth by its creators, and it was most commonly used to understand speech or speech development for autistic children. LENA is a useful tool for clinicians and caregivers to gain some insights into child speech, but those considering using it should be aware of concerns about its accuracy and limitations about the information it provides. In this review, we supplement the official LENA guidelines with specific suggestions for use with the autistic population.

Making a difference with matter in researchers’ positionality dynamics in qualitative inquiry

Scholars have increasingly highlighted the usefulness of new materialist theories and methodologies in attempts to address the perceived shortcomings of conventional theories inspired by social constructionism and post-structuralism. Contributing to these discussions, we utilize a new materialist theory which rests on a monistic ontology drawn from Spinozian and Deleuzian assemblage theory to examine the constitutive role of material elements (e.g. audio recorders, video cameras, and dress/shirts worn during interviews), spatial, and discursive forces in co-creating fluid nonstatic researcher positionalities in qualitative research process. This article is part of a larger ethnographic study conducted by the first author among fisherfolk in Ghana's coastal fishing communities. Our results show that the researcher's fluid positionalities during interview encounters were brought to bear and sustained in space and time through the joint effort of material, discursive, and spatial forces. As qualitative researchers seek ways to ensure better understanding of their study communities through intimate interactions, an attention to the assemblage of material-discursive forces in interview encounters may highlight some of the opportunities and obstacles in qualitative inquiry beyond human agency and negotiations.

Detection of tuberculosis using cough audio analysis: a deep learning approach with capsule networks

PurposeTuberculosis (TB) is a widespread infectious disease that requires early detection for effective treatment and control. This study aims to improve TB detection using cough audio analysis, comparing the performance of capsule networks to other deep learning models.MethodsWe used cough audio recordings from 1105 individuals with a new or worsening cough for at least two weeks, totaling 9772 recordings. These recordings were processed into spectral images, and HOG features were extracted. Various models, including Capsule Networks + FCNN, CNN, VGG16, and ResNet50 were trained and evaluated.ResultsCapsule Networks + FCNN achieved the best performance with an accuracy of 0.97, sensitivity of 0.98, specificity of 0.96, F1 score of 0.97, and precision of 0.97, outperforming other models. This attribute is due to the model’s ability to learn complex features from spectral images.ConclusionsThis study concludes that Capsule Networks are more effective than typical CNN-based models in diagnosing TB from cough audio. This suggests that advanced deep learning frameworks could significantly enhance TB screening accuracy, especially in resource-limited areas.