Audio Recordings Research Articles

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.

Pedagogical responsiveness: Focus on the Ukuqonda institute’s mode of engagement in mathematics

This paper was prompted by mathematics teachers’ challenges in implementing the proposed framework that centres on teaching for understanding, as opposed to teaching aimed at producing marks as evidence of achievement. Teaching for understanding in mathematics, among other factors, requires the creation of engaging and inclusive learning environments underpinned by teachers’ pedagogical responsiveness to the diverse needs of learners. We investigated pedagogical responsiveness, focusing on the Ukuqonda Institute’s mode of engagement in mathematics. We specifically pursued two research questions: 1) What are the key elements of the Ukuqonda Institute’s mode of engagement in mathematics? and 2) What characterised the pedagogical responsiveness of mathematics educators at the Ukuqonda Institute? We adopted collaborative autoethnography and used two data sets generated from audio recordings captured by the authors. We employed narrative analysis and organised the findings using the characteristics of pedagogical responsiveness as heuristic devices. The findings show that the participants’ pedagogical responsiveness was stimulated by the iterative process of team planning, deliberate implementation, and reflection. The prevalent characteristics were learner interactions, learner focus, inclusivity, dialogue and relationality, knowledge work, social justice, and equity. We recommend that similar studies be conducted targeting pedagogical responsiveness with a focus on other mathematical themes. Furthermore, this study suggests that, to remain pedagogically responsive, there should be constructive alignment among the types of tasks, questions, classroom interactions, and targeted content that underpin mathematics teaching and learning across different educational levels.

Moving Hearts with Audio Systems: The Past and Future of Acoustic Technology

Moving Hearts with Audio Systems: The Past and Future of Acoustic Technology

我抓在手里捏成棉花糖，什么烦恼不能忘: Learning Mandopop lyrics to promote bilingualism and biliteracy development

ABSTRACT Guided by heritage language and translanguaging theory, this ethnographic case study explores how a young second-generation Chinese American student used Mandopop lyrics to enhance her heritage language learning at home. Over six months, the mother, also the researcher collected 61 audio recordings of the student’s readings and singing of Mandopop, as well as translingual conversations between them. Supplemented with the researcher’s field notes, the analysis revealed significant improvements in the student’s pronunciation, Mandarin word recognition, oral language skills, and vocabulary. These improvements subsequently increased her oral translingual practices. Additionally, discussions about Mandopop lyrics enhanced the student’s higher-level thinking and understanding of her heritage culture. Overall, Mandopop lyrics effectively promote the student’s bilingual and biliteracy development. This study underscores the role of Mandopop lyrics in incorporating deep cultural elements, fostering bilingualism, and enhancing biliteracy. By engaging with Mandopop, the student connects with her heritage culture and improves her linguistic abilities in a meaningful and enjoyable way, highlighting the potential of music as a valuable tool in heritage language education.

A Review of the Challenges of Adaptive Filtering Technology in High-fidelity Audio Signal Processing

Abstract. High-fidelity audio signal processing plays an important role in modern audio technology. With the increasing demand for this technology in various audio application scenarios, the optimization of adaptive filters has emerged as a significant challenge in this field. This paper focuses on improving the performance of adaptive filters in high-fidelity audio signal processing which aims to improve the adaptability and efficiency of filters in complex audio environments by improving algorithms. In this study, the adaptive filtering algorithm based on wavelet transform and particle swarm optimization is used to verify the audio data processing by simulation and real data processing. The research data was collected using the standard audio signal database and the actual collected high-fidelity audio samples. The results show that the improved adaptive filter can significantly improve the performance of complex audio environments, improve the clarity and fidelity of audio signals and reduce the computational complexity. It is also suitable for real-time processing scenarios with limited resources. The conclusion shows that this method provides an efficient solution for high-fidelity audio signal processing and has a wide application prospect.

Designing a Business Profile Video to Increase Interest in Cooperation at the Forest Smoothie Company

Forest Smoothie faces challenges in increasing interest in cooperation with potential business partners. This research aims to design a Business Profile Video that can attract attention and increase cooperation interest in a Business-to-Business (B2B) context. The method used in this research is the pipeline method, which includes pre-production, production, and post-production stages. In the pre-production stage, needs analysis and video concept planning were conducted. The production stage involved shooting and audio recording, while the post-production stage included video editing and adding graphic elements. The results showed that the designed Business Profile Video was effective in conveying the company's message, increasing brand awareness, and attracting cooperation interest from potential business partners. Evaluation was conducted through a questionnaire that showed positive responses from respondents regarding message clarity, visual appeal, and increased interest in cooperating with Forest Smoothie.

Investigation of the Concept Images of Mathematics Educators and Preservice Mathematics Teachers Regarding Slope, Rate of Change, and Derivative

The aim of this study is to examine the concept images of mathematics educators and pre-service elementary mathematics teachers regarding the relationships between the concepts of slope, rate of change and derivative. Four mathematics educators working in different state universities and responsible for Analysis courses, three pre-service elementary mathematics teachers who successfully completed the Calculus 1 course at a state university, and four pre-service elementary mathematics teachers who successfully completed the Calculus 1 and Calculus 2 courses participated in the study. In order to determine the concept images of the participants about the concepts of slope, rate of change and derivative, the participants were asked semi-structured interview questions prepared by the researcher and application questions including the second stage questions. The audio recordings obtained from the interviews were transcribed and then the second stage questions were applied to the participants. The second stage questions were received in writing from the participants and analysed by the researcher through descriptive content analysis. As a result of this study, mathematics educators were able to use the concept images they had in the first stage questions in the second stage questions. On the other hand, pre-service elementary mathematics teachers were able to use the concept images they had in the first stage questions in the second stage questions.

A QUALITATIVE STUDY OF EFFECTIVE PEDAGOGICAL PRACTICES TO FOSTER JOY, CURIOSITY, AND WONDER IN MATHEMATICS AT ELEMENTARY STAGE

This Study Aims To Identify And Evaluate Effective Pedagogical Practices That Foster Joy, Curiosity, And Wonder Among Students In Mathematics Education At The Elementary Stage. The Study Employs A Qualitative Approach To Investigate The Impact Of These Practices On Students' Engagement And Enthusiasm For Mathematics. A Sample Of Mathematics Teachers From 10 Schools (20, Teachers) In The Varanasi District, India, Was Selected Randomly. Intelligent Verbatim Transcription Was Used To Convert Audio Recordings Into Text, Balancing Accuracy With Clarity By Omitting Unnecessary Fillers While Preserving The Essence Of The Conversations And Using NVIVO Employed To Facilitate Efficient Coding And Visualisation Of Connections Between Themes. The Analysis Process Will Involve Organizing The Transcribed Data, Qualitatively Identifying Themes And Patterns Related To Effective Pedagogical Practices To Foster 'Joy, Curiosity & Wonder' Among The Students In Mathematics At Elementary Stage, Combining The Benefits Of Observational Data With In-Depth Teacher Perspectives. The Findings Reveal A Positive Trend Towards More Student-Centered, Engaging, And Effective Teaching Strategies In Mathematics, While Also Indicating Opportunities For Further Development In Certain Areas. These Findings Have Significant Implications For Enhancing Student Engagement, Promoting Conceptual Understanding, And Encouraging A Growth Mind Set In Mathematics. This Study Emphasizes The Need For Policy Makers To Address Resource Disparities Between Schools And For Educators To Adopt Practices That Create Joyful, Curiosity-Driven Learning Environments, Ultimately Leading To Improved Student Outcomes And A More Positive Attitude Towards The Subject. KEYWORD: Mathematics Education, Pedagogy, Joy, Curiosity, Wonder, Student Engagement, Innovative Teaching Practices

Custodial Shadows: Lived Experiences of Postpartum Mothers Deprived of Liberty

Postpartum care is critical for women, particularly for those who are incarcerated, as they navigate both physical recovery and the unique challenges of their circumstances. Access to adequate healthcare within correctional systems remains severely limited, impacting the well-being of these women. While existing research has examined various prison-based programs—such as parenting classes, prison nurseries, and health initiatives—the voices and experiences of Postpartum Mothers Deprived of Liberty (PMDL) raising infants while imprisoned are often overlooked. This study aims to illuminate these experiences and how the prison environment influences their roles as mothers. Employing a descriptive phenomenological approach, this research involved a comprehensive literature review and purposive sampling to gather a targeted research sample. Specific criteria were established to identify eligible primary data sources. Data collection primarily utilized semi-structured interviews, allowing for open dialogue that facilitated a deep exploration of the informants' thoughts, beliefs, and experiences. Data analysis followed Colaizzi’s descriptive phenomenological method, ensuring credibility and trustworthiness through triangulation techniques, including audio recordings, field notes, pilot testing, and consultations with a research expert and psychometrician. Member checking was also conducted to verify the accuracy of the findings based on the informants' experiences. The analysis revealed five key themes: "Accepting the Inevitable: The Problems Arise After Birth," "Amusement Amidst Dilemma," "Supporting the Unsung: Building Bridges for Mothers Behind Bars," "Resilient Solitude: Embracing Inner Peace Amidst Maternal Separation," and "Maternal Bonds in Confinement: Underdeveloped Maternal Identity." The study concludes that while PMDLs engage in livelihood initiatives, skill development, and support networks, their separation from their infants significantly hampers their ability to fulfill maternal obligations and undermines their identity as mothers.

The effect of listening to the voice recording of relatives on chest pain, anxiety and depression in patients hospitalized in the coronary intensive care unit: A randomized controlled trial.

After acute myocardial infarction, the prevalence of anxiety and depression is quite high in patients because of severe chest pain, distance from relatives, unfamiliar environment and orientation problems. To assess the effect of listening to the voice recordings of relatives of patients with acute myocardial infarction who were treated in the coronary intensive care unit (ICU) on chest pain, anxiety and depression parameters of the patients. In the study, which was conducted as a randomized controlled trial, voice recordings of the family members of the patients were created and played to the patients through a music pillow. The study was carried out with 60 patients, 30 experimental and 30 control groups. Three tests were applied to the patients 15 min before, and 15 and 30 min after the application. The data of the study were collected using the Patient Introduction Form, Hospital Anxiety Depression Scale, Visual Analogue Scale and Patient Follow-up Form. It was found that there was a significant decrease in the anxiety level of the patients in the intervention group after listening to the audio recording (p < .001, 95% CI: -3.796; -0.070). However, there was no significant difference between the pain and depression scores of the control and intervention groups (p > .05). In the ICUs of patients with acute myocardial infarction, it may be recommended to play audio recordings of their relatives to reduce the severity of anxiety. In the intensive care setting, the use of voice recordings of relatives can be used as an effective, non-pharmacological intervention to reduce anxiety in patients with acute myocardial infarction. This approach may potentially improve overall recovery by reducing patient anxiety in the intensive care setting.

Hardware Implementation of a 2D Chaotic Map-Based Audio Encryption System Using S-Box

This paper presents a hardware-based audio encryption system using a 2D chaotic map and dynamic S-box design implemented on an Artix-7 FPGA platform. Three distinct chaotic maps—logistic–fraction (2D-LF), logistic–sine (2D-LS), and fraction–sine (2D-FS)—were investigated and implemented on an FPGA. The 2D-LF map was employed in the encryption system for its throughput and power efficiency performance. The proposed encryption system benefits from the randomness of chaotic sequences for block permutation and S-box substitution to enhance the diffusion and confusion properties of the encrypted speech signal. The system’s encryption strength is validated through performance evaluations, using the mean squared error (MSE), signal-to-noise ratio (SNR), correlation coefficients, and NIST randomness tests, which confirm the unpredictability of the encrypted speech signal. The hardware implementation results show a throughput of 2880 Mbps and power consumption of 0.13 W.

Workshop summaries from the 2024 voice AI symposium, presented by the Bridge2AI-voice consortium

IntroductionThe 2024 Voice AI Symposium, presented by the Bridge2AI-Voice Consortium, featured deep-dive educational workshops conducted by experts from diverse fields to explore the latest advancements in voice biomarkers and artificial intelligence (AI) applications in healthcare. Through five workshops, attendees learned about topics including international standardization of vocal biomarker data, real-world deployment of AI solutions, assistive technologies for voice disorders, best practices for voice data collection, and deep learning applications in voice analysis. These workshops aimed to foster collaboration between academia, industry, and healthcare to advance the development and implementation of voice-based AI tools.MethodsEach workshop featured a combination of lectures, case studies, and interactive discussions. Transcripts of audio recordings were generated using Whisper (Version 7.13.1) and summarized by ChatGPT (Version 4.0), then reviewed by the authors. The workshops covered various methodologies, from signal processing and machine learning operations (MLOps) to ethical concerns surrounding AI-powered voice data collection. Practical demonstrations of AI-driven tools for voice disorder management and technical discussions on implementing voice AI models in clinical and non-clinical settings provided attendees with hands-on experience.ResultsKey outcomes included the discussion of international standards to unify stakeholders in vocal biomarker research, practical challenges in deploying AI solutions outside the laboratory, review of Bridge2AI-Voice data collection processes, and the potential of AI to empower individuals with voice disorders. Additionally, presenters shared innovations in ethical AI practices, scalable machine learning frameworks, and advanced data collection techniques using diverse voice datasets. The symposium highlighted the successful integration of AI in detecting and analyzing voice signals for various health applications, with significant advancements in standardization, privacy, and clinical validation processes.DiscussionThe symposium underscored the importance of interdisciplinary collaboration to address the technical, ethical, and clinical challenges in the field of voice biomarkers. While AI models have shown promise in analyzing voice data, challenges such as data variability, security, and scalability remain. Future efforts must focus on refining data collection standards, advancing ethical AI practices, and ensuring diverse dataset inclusion to improve model robustness. By fostering collaboration among researchers, clinicians, and technologists, the symposium laid a foundation for future innovations in AI-driven voice analysis for healthcare diagnostics and treatment.

Dealing with Student Mistakes in Mathematics at Primary School

The article focuses on how teachers deal with student mistakes during mathematics instruction at primary school. The theoretical framework encompasses a constructivist culture of teaching and learning and dialogic teaching. Two general strategies are distinguished: avoiding mistakes and using mistakes as opportunities to learn. The presented qualitative study is based on 24 audio recordings of mathematics instruction, supplemented by interviews with six teachers. Through axial coding, we arrived at seven categories that describe specific ways of dealing with mistakes: not responding; making students aware of a mistake; encouraging students to present proofs; leading students to a level where they do not fail; expanding the student network of mathematical knowledge; creating opportunities for presenting content to clarify mistakes; and providing opportunities for students to find the cause of their mistakes. The findings are discussed in the context of the constructivist approach to instruction.

External Modifications of Requests among Jordanian University Students: A Socio-Pragmatic Analysis

The primary purpose of this study is to explore the external modifications of requests among Jordanian male and female university students in cross-gender settings and the factors affecting the choice of these strategies. The subjects of the study were 18 Jordanian undergraduate university students (9 males and 9 females) enrolled in different programs at Ajloun National University, Jordan. A mixed methodological approach was adopted for data collection. The data was retrieved from nine-hour audio recordings to gather naturally-occurring data and 18 DCTs to elicit organized data sets that can be analyzed based on patterns. Blum-Kulka et al.’s (1989) taxonomy of request strategies was espoused to analyze the obtained data. The data analysis revealed that the mitigating supportive moves (i.e., Imposition Minimizers, grounders, disarmers, preparators, getting a pre-commitment, promise of reward) were preferred by female students more than their male counterparts, whereas male students used Aggravating supportive moves (i.e., Threat, insult, Moralizing) more frequently than female students. Interestingly, other unique features that can be subsumed under Mitigating supportive moves manifested in Jordanian students’ requests, Namely, apology, self-introduction and gratitude. It was concluded that request strategies are not only used to fulfill certain needs, but also to manage social interactions and to strengthen relationships. Moreover, the way in which Jordanians use request strategies is strongly influenced by gender, cultural norms, and the context of interaction.

Empowering Music Education: Leveraging Digital Audio Technology in the Pursuit of Vocal Mastery – A Case Study of the Modern Popular Singing Course

Empowering Music Education: Leveraging Digital Audio Technology in the Pursuit of Vocal Mastery – A Case Study of the Modern Popular Singing Course

Development of a Marmoset Apparatus for Automated Pulling to study cooperative behaviors

In recent years, the field of neuroscience has increasingly recognized the importance of studying animal behaviors in naturalistic environments to gain deeper insights into ethologically relevant behavioral processes and neural mechanisms. The common marmoset (Callithrix jacchus), due to its small size, prosocial nature, and genetic proximity to humans, has emerged as a pivotal model toward this effort. However, traditional research methodologies often fail to fully capture the nuances of marmoset social interactions and cooperative behaviors. To address this critical gap, we developed the Marmoset Apparatus for Automated Pulling (MarmoAAP), a novel behavioral apparatus designed for studying cooperative behaviors in common marmosets. MarmoAAP addresses the limitations of traditional behavioral research methods by enabling high-throughput, detailed behavior outputs that can be integrated with video and audio recordings, allowing for more nuanced and comprehensive analyses even in a naturalistic setting. We also highlight the flexibility of MarmoAAP in task parameter manipulation which accommodates a wide range of behaviors and individual animal capabilities. Furthermore, MarmoAAP provides a platform to perform investigations of neural activity underlying naturalistic social behaviors. MarmoAAP is a versatile and robust tool for advancing our understanding of primate behavior and related cognitive processes. This new apparatus bridges the gap between ethologically relevant animal behavior studies and neural investigations, paving the way for future research in cognitive and social neuroscience using marmosets as a model organism.

Participative development of a culture-sensitive instrument to measure substance use in Syrian refugees

Abstract Background Rarely assessment instruments have been developed with end users such as refugees or those suffering from mental health conditions. Refugees’ experiences pre-, during, and post-flight are associated with various mental health problems including substance use disorders. Systematic reviews on the prevalence of substance use disorders in refugees worldwide show heterogeneous results. To address possible misclassification due to the lack of refugee-sensitive instruments we aimed to develop a refugee-sensitive instrument. Methods We applied a three-step triangulation study design. First, we conducted a three-stage delphi-process in 2019 and 2020. We recruited Syrian medical doctors for the study. Second, we conducted six focus group discussions with Syrian refugees and medical doctors. Third, we conducted expert checks with medical doctors and professionals providing psycho-social services for refugees. For all focus group discussions, audio recordings were translated and transcribed. Computer-assisted thematic analysis was performed applying a deductive approach with semantic coding. Results The refugee-sensitive instrument consists of seven domains of substance use: lifetime use of relevant types of substances, frequency, intensity, self-perception of, and situations posing a risk for substance use, ability to perform, craving, tolerance, and intentions to reduce or quit substance use. Discussion The instrument has been developed qualitatively, however, a limitation is that it could not be validated in a quantitative large sample of refugees. In spite of this limitation, this is - to the best of our knowledge - the first instrument that has been developed in a participatory approach together with end-users. Outlook The study suggests that developing assessment instruments in a participatory approach is feasible. Participatory development of assessment instruments is in line with the new paradigm of co-creation of mental health conditions management.