Audio Track Research Articles

Exposing tail biters by automatic scream detection

Tail biting is a major problem in pig husbandry and early intervention is essential to maintain animal health and welfare. To facilitate early identification of tail biters a detector software was created that can detect scream-linked biting events through analyzing video and audio recordings.Undocked weaner pigs housing in different pens and batches were recorded for a duration of 39 days. Scream-linked tail biting events were firstly identified manually and then automatically through the developed detector by analyzing the audio track of the video recordings. The detector's performance was evaluated by testing different sensitivity parameters (e.g., loudness threshold, call duration, frequency range).In four pens (748 h), a total of 2,898 screams were manually detected, with 52.8 % caused by tail biting. In the second step, 89.9 % of the detected screams were classified correctly as screams by the detector (precision 0.81–1.00). From the detected screams, 64.0 % were caused by tail biting. The detector automatically analyzes the latest videos in user-defined periods and sends warning messages if a threshold of screams per hour is exceeded. Then, biters can be identified manually using the detector extracted incidence video clips.In conclusion, automatic analysis of pig screams has high potential as an early intervention tool by detecting tail biting events followed by evaluation of time synchronized video clips for biter identification.

I Know It When I Hear It

In the following article I consider a catalog of audio description porn videos available on the online adult entertainment platform Pornhub. Attending to the visual and aural elements of the original source video and their simultaneous narration in the audio descriptive tracks, I argue that this transcription offers us, the viewer/auditor, an ekphrastic encounter with the pornographic moving image mediated by the acousmatic gendered voice of the audio describer. While academic scholarship on pornography informs my discussion of the source videos, theories of ekphrasis ranging from its usage in Ancient Greek rhetoric, to its formulation in twentieth-century anglophone literary theory, and finally to its application in digital visual culture, will underpin my analysis of the audio description. Through ekphrasis I ultimately distinguish the audio description of pornography as a creative genre in its own right, as well as offer an extensive and interdisciplinary approach that extends beyond the recursive or self-reflexive lens of porn studies scholarship, and newly positions hardcore film pornography within a larger body of academic inquiry in conversation with epic poetry and art history.

Self-Compassion is Associated with Improved Well-Being and Healthier Cortisol Profiles in Undergraduate Students

ObjectivesStress is highly prevalent in college students. Self-compassion, the tendency to respond in a caring manner to one’s own suffering or failures, reduces psychological distress and promotes mental health. Self-compassion may also influence physiological manifestations of stress; however, research is limited. Among undergraduate students over the course of an academic semester, we explored the associations of self-compassion with stress-related psychological variables including measures of affect, anxiety, and depressive symptoms. We also examined daily patterns of salivary cortisol over four days: diurnal slope, mean, and day-to-day cortisol rhythm stability.MethodThis sample of undergraduate students from introductory psychology courses in a large United States Midwestern university was predominantly non-Hispanic White (71.2%) and female (86.4%). All data were collected prior to final exams. After providing baseline psychosocial data, participants engaged in a 2-week mindfulness intervention: They were provided an iPod loaded with audio tracks based on the well-known Mindfulness-Based Stress Reduction intervention, but received no face-to-face instruction. Fifty-nine participants provided self-report demographic and medical data and completed the saliva sampling regimen over the first 4 days of the intervention. Diurnal salivary cortisol was assessed immediately after waking and again at bedtime over four consecutive days.ResultsHierarchical multiple regressions replicated previous findings showing that self-compassion is associated with higher positive and lower negative affect, lower perceived stress, and fewer symptoms of anxiety and depression. Regression models controlling for oral contraception and tobacco use revealed a positive association of self-compassion with healthy cortisol profiles marked by steeper diurnal cortisol slopes and increased regularity of the inter-daily cortisol slope.ConclusionsThese results confirm that self-compassion may be protective against the psychological and physiological manifestations of stress in college. Kind and compassionate responses to one’s own struggles may shield students from the adverse effects of stress. The potential mechanisms underlying these associations are worthy of future research.PreregistrationThis study is not preregistered.

Using knowledge graphs for audio retrieval: a case study on copyright infringement detection

Identifying cases of intellectual property violation in multimedia files poses significant challenges for the Internet infrastructure, especially when dealing with extensive document collections. Typically, techniques used to tackle such issues can be categorized into either of two groups: proactive and reactive approaches. This article introduces an approach combining both proactive and reactive solutions to remove illegal uploads on a platform while preventing legal uploads or modified versions of audio tracks, such as parodies, remixes or further types of edits. To achieve this, we have developed a rule-based focused crawler specifically designed to detect copyright infringement on audio files coupled with a visualization environment that maps the retrieved data on a knowledge graph to represent information extracted from audio files. Our system automatically scans multimedia files that are uploaded to a public collection when a user submits a search query, performing an audio information retrieval task only on files deemed legal. We present experimental results obtained from tests conducted by performing user queries on a large music collection, a subset of 25,000 songs and audio snippets obtained from the Free Music Archive library. The returned audio tracks have an associated Similarity Score, a metric we use to determine the quality of the adversarial searches executed by the system. We then proceed with discussing the effectiveness and efficiency of different settings of our proposed system.Graphical abstract

Holy Moly

In this fast-paced choose-your-own-adventure performance, Holy Moly offers multiple truths, allowing everyone to walk away with a slightly different experience. Based on choices made as an audience member, each person will receive one of multiple collaged audio tracks on a personal cassette tape. These multiple tracks, Beanie Babies, Jazzercise, cooking shows, and Schexnider’s own childhood field recordings are used to recover a feeling of holiness. It is a ritualistic grab bag of the sacred in the everyday in a search for connection and wholeness.

Firefly algorithm-based LSTM model for Guzheng tunes switching with big data analysis

Guzheng tune progression involves intricately harmonizing melodic motif transitions. Effectively navigating this vast creative possibility space to expose musically consistent elaborations presents challenges. We develop a specialized large long short-term memory (LSTM) model for generating musically consistent Guzheng tune transitions. First, we propose novel firefly algorithm (FA) enhancements, e.g., adaptive diversity preservation and adaptive swim parameters, to boost exploration effectiveness for navigating the vast creative combinatorics when generating Guzheng tune transitions. Then, we develop a specialized stacked LSTM architecture incorporating residual connections and conditioned embedding vectors that can leverage long-range temporal dependencies in Guzheng music patterns, including unsupervised learning of concise Guzheng-specific melody embedding vectors via a variational autoencoder, encapsulating unique harmonic signatures from performance descriptors to provide style guidance. Finally, we use LSTM networks to develop adversarial generative large models that enable realistic synthesis and evaluation of Guzheng tunes switching. We gather an extensive 10+ hour corpus of solo Guzheng recordings spanning 230 musical pieces, 130 distinguished performing artists, and 600+ audio tracks. Simultaneously, we conduct thorough Guzheng data analysis. Comparative assessments against strong baselines over systematic musical metrics and professional listeners validate significant generation fidelity improvements. Our model achieves a 63 % reduction in reconstruction error compared to the standard FA optimization after 1000 iterations. It also outperforms baselines in capturing characteristic motifs, maintaining modality coherence with under 2 % dissonant pitch errors, and retaining desired rhythmic cadences. User studies further confirm the superior naturalness, novelty, and stylistic faithfulness of the generated tune transitions, with ratings close to real data.

CLASSIFICATION OF KAZAKH MUSIC GENRES USING MACHINE LEARNING TECHNIQUES

This article analysis a Kazakh Music dataset, which consists of 800 audio tracks equally distributed across 5 different genres. The purpose of this research is to classify music genres by using machine learning algorithms Decision Tree Classifier and Logistic regression. Before the classification, the given data was pre-processed, missing or irrelevant data was removed. The given dataset was analyzed using a correlation matrix and data visualization to identify patterns. To reduce the dimension of the original dataset, the PCA method was used while maintaining variance. Several key studies aimed at analyzing and developing machine learning models applied to the classification of musical genres are reviewed. Cumulative explained variance was also plotted, which showed the maximum proportion (90%) of discrete values ​​generated from multiple individual samples taken along the Gaussian curve. A comparison of the decision tree model to a logistic regression showed that for f1 Score Logistic regression produced the best result for classical music - 82%, Decision tree classification - 75%. For other genres, the harmonic mean between precision and recall for the logistic regression model is equal to zero, which means that this model completely fails to classify the genres Zazz, Kazakh Rock, Kazakh hip hop, Kazakh pop music. Using the Decision tree classifier algorithm, the Zazz and Kazakh pop music genres were not recognized, but Kazakh Rock with an accuracy and completeness of 33%. Overall, the proposed model achieves an accuracy of 60% for the Decision Tree Classifier and 70% for the Logistic regression model on the training and validation sets. For uniform classification, the data were balanced and assessed using the cross-validation method. The approach used in this study may be useful in classifying different music genres based on audio data without relying on human listening.

Extracting Audio from Image Using Machine Learning

This study introduces a new method for extracting sound from pictures by utilizing machine learning. Lately, there has been a lot of excitement around multi-modal learning because of its ability to reveal valuable information from various sources, like images and sound. Our research is centered on using the unique qualities of visual and auditory signals to predict sound content from pictures. This opens up possibilities for enhancing accessibility, creating content, and providing immersive user experiences. We start by exploring previous research in multi-modal learning, audio-visual processing, and tasks like image captioning and sound source localization. Based on this background, we introduce an approach that merges convolutional neural networks (CNNs) for image analysis with recurrent neural networks (RNNs) or transformers for sequence interpretation. The system is educated on a collection of matched images and associated audio tracks, allowing it to grasp the intricate connections between visual and auditory data. In our study, we carefully assessed the performance of our proposed method by using well-known metrics. We measure how well our method works by comparing it to other methods and showing that it can accurately and quickly extract audio from images. We also show through qualitative analysis that our model can create clear audio representations from a variety of visual inputs. After a thorough discussion, we analyze the findings, pointing out both the advantages and drawbacks of our method. We pinpoint potential areas for further study, such as delving into more advanced structures and incorporating semantic data to enhance audio extraction. To sum up, this study adds to the expanding field of multi-modal learning by introducing a promising model for extracting audio from images through machine learning. Our results emphasize the potential of this technology to improve accessibility, inspire creativity, and increase user engagement in different fields. Key Words: Audio Extraction, Machine Learning, Computer Vision, Deep Learning, Convolutional Neural Networks

Background music monitoring framework and dataset for TV broadcast audio

AbstractMusic identification is widely regarded as a solved problem for music searching in quiet environments, but its performance tends to degrade in TV broadcast audio owing to the presence of dialogue or sound effects. In addition, constructing an accurate dataset for measuring the performance of background music monitoring in TV broadcast audio is challenging. We propose a framework for monitoring background music by automatic identification and introduce a background music cue sheet. The framework comprises three main components: music identification, music–speech separation, and music detection. In addition, we introduce the Cue‐K‐Drama dataset, which includes reference songs, audio tracks from 60 episodes of five Korean TV drama series, and corresponding cue sheets that provide the start and end timestamps of background music. Experimental results on the constructed and existing datasets demonstrate that the proposed framework, which incorporates music identification with music–speech separation and music detection, effectively enhances TV broadcast audio monitoring.

An organic artificial soma for spatio-temporal pattern recognition via dendritic integration

A novel organic neuromorphic device performing pattern classification is presented and demonstrated. It features an artificial soma capable of dendritic integration from three pre-synaptic neurons. The time-response of the interface between electrolytic solutions and organic mixed ionic-electronic conductors is proposed as the sole computational feature for pattern recognition, and it is easily tuned in the organic dendritic integrator by simply controlling electrolyte ionic strength. The classifier is benchmarked in speech-recognition experiments, with a sample of 14 words, encoded either from audio tracks or from kinematic data, showing excellent discrimination performances in a planar, miniaturizable, fully passive device, designed to be promptly integrated in more complex architectures where on-board pattern classification is required.

Audio Stream Analysis for Deep Fake Threat Identification

This article introduces a novel approach for the identification of deep fake threats within audio streams, specifically targeting the detection of synthetic speech generated by text-to-speech (TTS) algorithms. At the heart of this system are two critical components: the Vocal Emotion Analysis (VEA) Network, which captures the emotional nuances expressed within speech, and the Supervised Classifier for Deepfake Detection, which utilizes the emotional features extracted by the VEA to distinguish between authentic and fabricated audio tracks. The system capitalizes on the nuanced deficit of deepfake algorithms in replicating the emotional complexity inherent in human speech, thus providing a semantic layer of analysis that enhances the detection process. The robustness of the proposed methodology has been rigorously evaluated across a variety of datasets, ensuring its efficacy is not confined to controlled conditions but extends to realistic and challenging environments. This was achieved through the use of data augmentation techniques, including the introduction of additive white noise, which serves to mimic the variabilities encountered in real-world audio processing. The results have shown that the system's performance is not only consistent across different datasets but also maintains high accuracy in the presence of background noise, particularly when trained with noise-augmented datasets. By leveraging emotional content as a distinctive feature and applying sophisticated machine learning techniques, it presents a robust framework for safeguarding against the manipulation of audio content. This methodological contribution is poised to enhance the integrity of digital communications in an era where synthetic media is proliferating at an unprecedented rate.

The use of the iBrainstorm app in a collaborative argumentation-based learning context for developing listening comprehension skills by EFL learners

The present study investigated the use of the iBrainstorm app in a collaborative argumentation-based learning context for developing listening comprehension skills by EFL learners. Two groups of students were formed. All of them studied English as a foreign language at the BA level at Bu-Ali Sina University, Iran. Participants were assigned to groups at random. Participants took a pre-test of listening comprehension skills before starting the programme. The control group listened to authentic audio tracks in English and discussed their contents, watched authentic English movies, discussed issues in the movies in pairs in the classroom. The experimental group spent part of the time on theoretical explanation of, and practical exercises with, argumentation-based learning by the iBrainstorm application. The total instruction time was the same for two groups, i.e., 32 hours. Students then took a post-test and, a month later, a delayed post-test in listening comprehension skills. The results show that the use of the iBrainstorm app significantly improved the students’ listening comprehension skills, and significantly more so than those of the control group. These results have pedagogical implications for curriculum designers, material producers, and all who are involved in language study and pedagogy.

An Analysis of ELF-informed Practices in ESP Coursebooks

The investigation of English as a Lingua Franca (ELF) in English for Specific Purposes (ESP) contexts has produced significant results in the last few years. Moreover, these results have initiated a shift from achieving native speaker competency to more context-related and functional language use in the perspective of the overall approach to ESP. Yet, the literature needs more study to reveal how far this shift has embedded ESP coursebooks and audio materials. Therefore, this study aimed to explore to what extent the recent ESP coursebooks and audio materials matched the characteristics of ELF. In the study, four ESP coursebooks and their audio tracks were analyzed in terms of the presence or absence of references to ELF features, specifically; ELF-informed activities, the promotion of using English outside the inner circle countries, and the use of authentic expending circle English communication. The findings revealed the dominance of Standard English in language exposure, a dearth of ELF-informed activities, and a sparse representation of expending circle cultures in the four ESP coursebooks. Similarly, the listening tracks showed a strong preference for native English speakers as the introducers of English users in the tracks. The study presents a number of critical implications for ESP instructors and material designers.

Secure and resilient improved image steganography using hybrid fuzzy neural network with fuzzy logic

The exponential growth in communication networks, data technology, advanced libraries, and mainly World Wide Web services has played a pivotal role in facilitating the retrieval of various types of information as needed. However, this progress has also led to security concerns related to the transmission of confidential data. Nevertheless, safeguarding these data during communication through insecure channels is crucial for obvious reasons. The emergence of steganography offers a robust approach to concealing confidential information, such as images, audio tracks, text files, and video files, in suitable media carriers. A novel technique is envisioned based on back-propagation learning. According to the proposed method, a hybrid fuzzy neural network (HFNN) is applied to the output obtained from the least significant bit substitution of secret data using pixel value differences and exploiting the modification direction. Through simulation and test results, it has been observed that the proposed methodology achieves secure steganography and superior visual quality. During the experiments, we observed that for the secret image of the cameraman, the PSNR & MSE values of the proposed technique are 61.963895 and 0.041361, respectively.

A Systematic Literature Review: Facial Expression and Lip Movement Synchronization of an Audio Track

A Systematic Literature Review: Facial Expression and Lip Movement Synchronization of an Audio Track

Metaphorical Expression of Emotions in Modern Music Composition Based on Emotional Calculations

Abstract In this paper, audio and lyrics features of music are fused from the audio and lyrics attributes of modern music tracks to obtain a joint representation of music. The features such as tempo, directionality, average value of intensity, beat, and change of rhythm of each musical segment are extracted from the main audio track to form the music feature vector. Subsequently, the music was separated into multiple segments with distinct emotions, and the emotional expression of modern music was evaluated using the Hevner emotion model. Finally, the note extraction performance of this paper’s model is analyzed, and the spectral contrast features of different music pieces and the emotional expression of music pieces under different features are explored. The results show that the pitch patterns of sad emotions are mostly distributed in the range of 0.5-0.55, and the values of the pitch patterns of angry music are basically larger than 0.55. The mean values of the spectral entropy of joy and calmness are mostly distributed in the range of 0.5-0.7, and the sad emotions are mostly in the vicinity of 0.7, while the mean values of the spectral entropy of angry emotions are larger than 0.8.

Key challenges in using automatic dubbing to translate educational YouTube videos

The dubbing industry has been particularly concerned with how to cope with the higher demand in dubbing experienced over the past few years. Media companies have invested in Artificial Intelligence, with significant developments on automatic dubbing spearheaded by companies like Google (Kottahachchi & Abeysinghe, 2022), Amazon (Federico et al., 2020; Lakew et al., 2021) or AppTek (Di Gangi et al., 2022). These organisations have clearly seen the potential in automatic dubbing, understood as the combination of automatic speech recognition, machine translation and text to speech technologies to automatically replace the audio track of an original audiovisual text with synthetic speech in a different language, taking into consideration relevant synchronies. Against this backdrop, this article sets out to: 1) provide an overview of automatic dubbing in the current mediascape and to contextualise this practice accordingly; and 2) to identify some of the main challenges of its implementation, especially as regards the integration of MT and speech synthesis in the dubbing workflow. To this end, the performance of the tool Aloud will be evaluated, by analysing the videos currently available in the Spanish version of the YouTube Channel Amoeba Sisters, which have been dubbed using this tool. The evaluation will focus on the issues highlighted by YouTube users in their comments on this YouTube channel, which include naturalness and accuracy. Special attention will be paid to the use of synthetic voices, which are heavily criticised by users. However, they also highlight the usefulness of automatic dubbing for students interested in biology-related topics who are not fluent in English, in line with the original intent of the tool developers of increasing accessibility.

Цифровые технологии пропуска по перегонам и станциям — основа организации движения на Московских центральных диаметрах

train separation, automatic block system, ABTC-MSh system, moving block, interlocking, automatic cab signalling, train control system The article discusses the development of automatic block systems, which form the basis of separation systems. It also highlights the key factors limiting the capacity on open lines, and ways to solve them. A brief overview of the foreign experience of the organization of train separation using automatic block system based on track circuits is given. The article shows the capabilities and role of the computerbased automatic block signalling system with a centralized placement of equipment, audio frequency track circuits and duplicating information transmission channels as an important element of the train traffic management at the sections of Moscow Central Diameters. The significance of the implemented non-stop passage of trains along the main station tracks providing substantial section capacity increase is demonstrated. The necessity of building a digital system for train spacing is shown, which makes it possible to implement the moving block technology with-in the station ensuring the movement of trains on open lines and at stations with the same headway. The advantages of a new type of the computer-based automatic block signalling system as a basic element of a promising Russian train traffic control system and the positive effects of its implementation on the Russian railway network are indicated. The direction of development of train separation systems is outlined within the framework of further digitalization.

A deep learning-based telemonitoring application to automatically assess oral diadochokinesis in patients with bulbar amyotrophic lateral sclerosis

Background and objectivesTimely identification of dysarthria progression in patients with bulbar-onset amyotrophic lateral sclerosis (ALS) is relevant to have a comprehensive assessment of the disease evolution. To this goal literature recognized the utmost importance of the assessment of the number of syllables uttered by a subject during the oral diadochokinesis (DDK) test. MethodsTo support clinicians, this work proposes a remote deep learning-based system, which consists (i) of a web application to acquire audio tracks of bulbar-onset ALS patients and healthy control subjects while performing the oral DDK test (i.e., repeating the /pa/, /pa-ta-ka/ and /oo-ee/ syllables) and (ii) a DDK-AID network designed to process the acquired audio signals which have different duration and to output the number of per-task syllables repeated by the subject. ResultsThe DDK-AID network overcomes the comparative method achieving a mean Accuracy of 90.23 in counting syllables repeated by the eleven bulbar-onset ALS-patients while performing the oral DDK test. ConclusionsThe proposed remote monitoring system, in the light of the achieved performance, represents an important step towards the implementation of self-service telemedicine systems which may ensure customised care plans.

Toward Burnout Prevention: Can One Short Virtual Reality Relaxation and Mindfulness Training Session for Staff and Patients Decrease Stress and Improve Subjective Sense of Wellbeing?

Mental wellness of healthcare workers has deteriorated recently, increasing burnout rates. Cancer patients are also often highly distressed, reporting fear, pain, and fatigue. Relaxation and mindfulness training have been shown to decrease stress and anxiety. Currently, the use of virtual reality (VR) for relaxation and mindfulness for cancer patients and oncology clinical staff is an ongoing area of research. We aimed to test the preliminary efficacy of incorporating an innovative digital therapeutic (DTx) we developed at our center in this population. Cancer patients and clinic staff from one institution's Gastrointestinal and Radiation Oncology departments participated in the immersive VR-enhanced relaxation and mindfulness experience for this IRB-exempt study. Users completed a pre-VR survey via iPad assessing baseline knowledge and practice of stress reduction techniques, baseline stress, and familiarity with VR. In the VR app deployed on an Oculus Quest 2, users chose a relaxing water scene (e.g., stream, beach) and optional soothing background music. Users could also choose a relaxation or mindfulness training audio track. A post-VR survey assessed whether the experience affected their subjective stress and sense of wellbeing ("Yes" or "No") as well as the feasibility of using the app. A binomial test on a single proportion was used to test whether more participants (>50%) indicated their stress was reduced following the VR training than did not. Post-VR qualitative verbal feedback was also collected to identify future changes to the VR app. Six patients, a patient's son, and forty-three employees used the VR app. Users were aged ≤ 30 years old (18%), 30-50 years (60%), and 50-70 years (22%). Users completed the VR experience in a median of 14 min (IQR: 11-19 min). In the pre-survey, most (78%) reported they felt stress at this point in their lives. In the post-survey, significantly more than the expected proportion of participants (>50%) reported feeling less stressed after using the VR app (88%, n = 44, p <0.001). Most (90%) reported that the VR app improved their subjective sense of wellbeing. All (100%) users reported it was easy to learn the VR controls. Nearly all (96%) reported they would be interested in using this VR app again, including 30% and 38% who reported they would be "extremely likely" and "very likely," respectively, to use the app again. These findings suggest our VR relaxation and mindfulness training was well accepted and could be integrated into the hospital setting in short sessions. Further work should be done based on participant feedback to expand the offerings of this VR app to offer a wider range of relaxation experiences and gamified psychological interventions that can help de-stress, recharge, and build resiliency.