Audio Editing Research Articles

Reshaping the Sound Landscape: The Application and Development of AI in the Sound Creation of Chinese Podcasts in the Era of Intelligent Media

With the rapid development of intelligent media technology, AI has greatly enriched the creation means and expression forms of Chinese podcasts and reshaped the diversity and personalization of speech synthesis, audio editing and content generation, through the diversity and personalization of sound landscape. Through the specific application cases of AI in the creation of Chinese podcast voice, this paper analyzes its positive effects in improving the efficiency of creation, optimizing user experience and promoting the development of the industry, and looks forward to the future development trend and challenges, aiming to provide valuable reference and inspiration for the development of the field of Chinese podcast

The possibility of the application of modern vocal music technology in vocal music education / La potencial aplicación de las nuevas tecnologías de la música vocal en la enseñanza de la música vocal

Information technologies in the modern world cover many fields of activity, including education. This contributes to the transformation of the educational process and the development of students’ independence. The main purpose of this paper is to assess the possibilities of using modern vocal music technologies in Chinese music education. To achieve the above purpose, the authors of the manuscript analysed the data obtained and divided the interactive technologies that can be used for vocal music education into the following four groups: software for studying theoretical frameworks, universal software, spectrogram software and audio editing software. The selected applications help learners acquire extensive vocal knowledge. Using the Likert scale, the researchers found that the applications of preference chosen by the respondents in each of the presented groups were Explain Everything (93%), Sing Sharp (87%), Sodaphonic (73%) and MAGIX Music Maker (82%). Sing Sharp provides vocal lessons in the form of a game. Sodaphonic eliminates low-quality performance elements in the process of creation of audio files. MAGIX Music Maker helps users create new songs using virtual musical instruments.

Creating Interactive Scenes in 3D Educational Games: Using Narrative and Technology to Explore History and Culture

Three-dimensional games are an indispensable tool in education and cultural transmission, offering users immersive experiences that facilitate learning through engagement and direct experience. The aim of this study was to design and implement an advanced cutscene sequencer in Unity 3D, targeted at educational and cultural games, to assist game developers in producing cinematic interludes, which are a key narrative element in games. The project methodology encompassed a detailed process of planning, design, and implementation. This involved the comprehensive use of various tools, including Unity 3D for game development, C# for scripting, Visual Studio for integrated development, Git for version control, Blender for 3D modeling, Substance Painter for texturing, and Audacity for audio editing. These tools collectively facilitated the development of a robust cutscene sequencer system designed to create engaging and dynamic narrative scenes. The project’s results indicate that the use of an advanced sequencer can significantly impact the efficiency and creativity of the game and educational material creation process, offering developers the opportunity to explore practically unlimited viewing perspectives. This tool enables the creation of rich and diverse visual experiences, which is crucial for engaging and educating players.

Pyramid Feature Attention Network for Speech Resampling Detection

Speech forgery and tampering, increasingly facilitated by advanced audio editing software, pose significant threats to the integrity and privacy of digital speech avatars. Speech resampling is a post-processing operation of various speech-tampering means, and the forensic detection of speech resampling is of great significance. For speech resampling detection, most of the previous works used traditional methods of feature extraction and classification to distinguish original speech from forged speech. In view of the powerful ability of deep learning to extract features, this paper converts the speech signal into a spectrogram with time-frequency characteristics, and uses the feature pyramid network (FPN) with the Squeeze and Excitation (SE) attention mechanism to learn speech resampling features. The proposed method combines the low-level location information and the high-level semantic information, which dramatically improves the detection performance of speech resampling. Experiments were carried out on a resampling corpus made on the basis of the TIMIT dataset. The results indicate that the proposed method significantly improved the detection accuracy of various resampled speech. For the tampered speech with a resampling factor of 0.9, the detection accuracy is increased by nearly 20%. In addition, the robustness test demonstrates that the proposed model has strong resistance to MP3 compression, and the overall performance is better than the existing methods.

“Stay tuned!"

“Stay tuned!"

Auditory Learner

Auditory Learner

From Niche Narrative to Audio Blockbusters

From Niche Narrative to Audio Blockbusters

Beat-to-beat alterations of acoustic intensity and frequency at the maximum power of heart sounds are associated with NT-proBNP levels.

Auscultatory features of heart sounds (HS) in patients with heart failure (HF) have been studied intensively. Recent developments in digital and electrical devices for auscultation provided easy listening chances to recognize peculiar sounds related to diastolic HS such as S3 or S4. This study aimed to quantitatively assess HS by acoustic measures of intensity (dB) and audio frequency (Hz). Forty consecutive patients aged between 46 and 87 years (mean age, 74 years) with chronic cardiovascular disease (CVD) were enrolled in the present study after providing written informed consent during their visits to the Kitasato University Outpatient Clinic. HS were recorded at the fourth intercostal space along the left sternal border using a highly sensitive digital device. Two consecutive heartbeats were quantified on sound intensity (dB) and audio frequency (Hz) at the peak power of each spectrogram of S1-S4 using audio editing and recording application software. The participants were classified into three groups, namely, the absence of HF (n = 27), HF (n = 8), and high-risk HF (n = 5), based on the levels of NT-proBNP < 300, ≥300, and ≥900 pg/ml, respectively, and also the levels of ejection fraction (EF), such as preserved EF (n = 22), mildly reduced EF (n = 12), and reduced EF (n = 6). The intensities of four components of HS (S1-S4) decreased linearly (p < 0.02-0.001) with levels of body mass index (BMI) (range, 16.2-33.0 kg/m2). Differences in S1 intensity (ΔS1) and its frequency (ΔfS1) between two consecutive beats were non-audible level and were larger in patients with HF than those in patients without HF (ΔS1, r = 0.356, p = 0.024; ΔfS1, r = 0.356, p = 0.024). The cutoff values of ΔS1 and ΔfS1 for discriminating the presence of high-risk HF were 4.0 dB and 5.0 Hz, respectively. Despite significant attenuations of all four components of HS by BMI, beat-to-beat alterations of both intensity and frequency of S1 were associated with the severity of HF. Acoustic quantification of HS enabled analyses of sounds below the audible level, suggesting that sound analysis might provide an early sign of HF.

Cross-platform adaptation of algorithmic editing techniques

The research relevance is determined by the rapid development of technology and the growing need for efficient data processing on various platforms. The study aimed to address methods that would enable the use of data editing algorithms on various operating systems and hardware platforms. A methodology was developed for studying cross-platform adaptation technologies, including cross-compilation, virtualisation, the use of universal libraries and Application Programming Interface, as well as methods for testing and optimising algorithm performance. The study addressed various approaches to implementing cross-platform compatibility, including the use of cross-compilation, virtualisation and containerisation. The main technical challenges are managing resources, optimising performance and ensuring compatibility with hardware from different platforms. The principles included selecting the most appropriate technology for the task at hand, considering performance and security requirements, and ensuring effective integration of existing systems and infrastructure. The workflows are focused on creating modular and extensible solutions that can easily adapt to changes in the technological environment and user requirements. In the context of this study, artificial intelligence software plays a key role in improving the efficiency and accuracy of data processing across different platforms. The results showed that artificial intelligence software can automate various stages of the video and audio editing process. Artificial intelligence is used to analyse large amounts of content data, such as video files, images and audio recordings. The study determined that artificial intelligence is increasingly relevant in various aspects of movie production. Artificial intelligence can analyse scripts, predict their potential success and suggest improvements using data from previous films and their commercial success

Detecting Forged Audio Files Using "Mixed Paste" Command: A Deep Learning Approach Based on Korean Phonemic Features.

The ubiquity of smartphones today enables the widespread utilization of voice recording for diverse purposes. Consequently, the submission of voice recordings as digital evidence in legal proceedings has notably increased, alongside a rise in allegations of recording file forgery. This trend highlights the growing significance of audio file authentication. This study aims to develop a deep learning methodology capable of identifying forged files, particularly those altered using "Mixed Paste" commands, a technique not previously addressed. The proposed deep learning framework is a composite model, integrating a convolutional neural network and a long short-term memory model. It is designed based on the extraction of features from spectrograms and sequences of Korean consonant types. The training of this model utilizes an authentic dataset of forged audio recordings created on an iPhone, modified via "Mixed Paste", and encoded. This hybrid model demonstrates a high accuracy rate of 97.5%. To validate the model's efficacy, tests were conducted using various manipulated audio files. The findings reveal that the model's effectiveness is not contingent on the smartphone model or the audio editing software employed. We anticipate that this research will advance the field of audio forensics through a novel hybrid model approach.

The Utilization of Smartphone Technology as A Medium for Creating Audiovisual Content in SMA Trensains Muhammadiyah Sragen

ABSTRACT. Audiovisual learning has become an increasingly popular method in modern education. This method used audiovisual technology to produce more interactive, engaging, and effective learning. In addition to instructional materials, audiovisual content such as films, advertisements, and other videos can also be utilized as promotional tools for schools through social media platforms like YouTube and others.&#x0D; SMA Trensains Muhammadiyah Sragen is one of the best schools that has achieved numerous accomplishments. It is managed by the Muhammadiyah Regional Leadership (Pimpinan Daerah Muhammadiyah/PDM) in Sragen, Central Java. SMA Trensains Muhammadiyah Sragen also has a film production-focused community. The audiovisual content produced by SMA Trensains will help highlight school publications and student achievements. Despite having a community, there are still shortcomings regarding the depth of cinematography knowledge, lack of audio recording equipment, and underutilization of smartphones, which can also serve as video cameras. Therefore, dedication is made through training in utilizing smartphones as a means to create audiovisual content, aiming to enhance students' skills and abilities. The training also aims to boost students' creativity in creating and producing captivating and high-quality audiovisual works using simple equipment.&#x0D; The method used in this training, students are taught about the use of smartphone technology and the applications that can be used. Students will also be taught about the basic techniques in imaging, video, and audio editing, as well as processing content to look professional and engaging. In addition, students are also trained in terms of developing creative ideas and creating a content media production plan that is systematic and measured. In addition to training, the dedicated team also provides a set of production tools such as vlogging kits, lighting, and clips on Saramonic with the aim that in addition to focusing on imaging, students also understand the importance of audio in the creation of audiovisual content

New Game Artificial Intelligence Tools for Virtual Mine on Unreal Engine

Currently, the gamification of virtual reality for training miners, especially for emergencies, and designing the extraction of minerals in difficult technological conditions has been embodied in the Virtual Mine software and hardware. From a software development point of view, Virtual Mine is indistinguishable from other virtual reality games, and this offers a chance to use the potential of rapidly developing game software in mining, including engines, 3D modeling tools, audio editors, etc., to solve a wide range of game development tasks. The chosen direction will optimize the work of developers by providing a tool for developing game artificial intelligence to solve problems that require implementing the behavior of game agents without using a rigidly defined choice of scenarios or chains of these scenarios. The aim of the work is to expand the possibilities of working with game artificial intelligence on the Unreal Engine game engine to make it more functional. As a result, a tool has been obtained that can be used to optimize the time and improve the quality of the development of game artificial intelligence for Virtual Mine using flexible development approaches. The asset editor was developed, application modes and their working tabs were defined, and a graphical node system for the behavioral graph editor was created. A system for executing a behavioral graph is given; algorithms for its operation and features for executing nodes of a behavioral graph are presented.

Skin Cortisol and Acoustic Activity: Potential Tools to Evaluate Stress and Welfare in Captive Cetaceans.

As people's focus broadens from animals on farms to zoos and aquaria, the field of welfare science and the public's concern for animal welfare continue to grow. In captive animals, stress and its causes are topics of interest in welfare issues, and the identification of an objective method that can be used to assess animals' stress as a physiological state is essential. Both behavioral and physiological parameters can be used as indicators in order to assess animal stress quantitatively. To validate this approach, acoustic activity and the sloughed scrape skin cortisol concentration were used to evaluate the animal welfare of captive beluga whales (Delphinapterus leucas). The acoustic activity (5 min at 10:00 am) of three captive D. leucas was routinely recorded by a transducer and analyzed using audio editing software. The calls were separated into three main categories: whistles, pulses, and combo calls. The sloughed scrape skin samples were collected non-invasively once a week from all three animals' fluke and/or flipper. Cortisol was extracted using a modified skin steroid extraction technique, and detected via commercially available enzyme immunoassays. The results showed that the cortisol concentration increased by varying levels when the whales encountered the same event. In addition, the number and distribution of the calls changed along with the events. This indicated that the changes in the cortisol concentration and acoustic behavior may have reflected the fluctuations in the environment and body condition. Therefore, the scrape cortisol measurement and acoustic recordings could be used to monitor stress levels in captive beluga whales. We recommend that aquaria consider incorporating skin scrape cortisol and acoustic activity monitoring into their standards for animal welfare.

‘Listening closely’ to mediated intimacies and podcast intimacies inSong Exploder

Intimacy is an important and growing concept in both media studies and podcast studies. But research regarding intimacies in both disciplines has yet to fully account for the connection between sound and normativity, which is essential to podcasting and important to mediated intimacies more broadly. In this article, we mobilise scholarship from these two fields to analyse the award-winning music podcast Song Exploder. Our study highlights that attending to intimacies in podcasting involves both analysing how the story structure aligns with social norms and listening critically to the ways the sound design and audio editing complements and complicates these intimate stories. We contend that identifying the intersection of sound and normativity in this podcast contributes to understanding the cultural work of podcasting and underscores the key role of sound in mediated intimacies.

Peculiarities of teaching the academic discipline “Quartet class” in distance learning conditions

The relevance of the article is due to the new realities of today, namely, the transition of most Ukrainian educational institutions to distance learning. This has caused a change in the approach to the educational process and proved the importance of media literacy of educators, their knowledge and mastery of Internet technologies and the introduction of various useful applications into the curriculum.&#x0D; The purpose of the article is to overview the innovations of the educational process in modern realities, provide a list of tools and demonstrate the implementation of individual applications capable of modernizing online learning and helping to achieve efficient and high-quality results.&#x0D; The methodology. The purpose and objectives of the research have determined its methodology. Methods of empirical knowledge, systematization and generalization have formed the fundamental basis of the study.&#x0D; The results. The article highlights the peculiarities of the online learning process. Special attention is paid to the need to improve the media literacy of educators. An overview has been made and references have been chosen for courses, webinars, seminars, online platforms for professional development in the field of digital technologies. It has been proved that such software as Audacity, BandLab, Audio Editor Hokusai, Reaper, Samplitude, Cubase and the following online resources Audio-Joiner, Mp3cut.foxcom, clideo.com, filesmerge.com, solveigmm.com, mp3food.com have become useful in the process of teaching.&#x0D; Specific examples of the use of Google’s digital tools have been offered, including Google Classroom, Google form, Google sites. The study has also revealed the importance of individual student work and a systematized list of forms of independent student work in the quartet class has been provided, among them: listening to a given quartet composition; work with a quartet score; understanding of the form of musical works, their semantic load; learning the musical text, taking into account all the composer’s notes; selection of the most profitable application; arrangement of beats and their coordination between members of the ensemble; development of pausing and its coordination with other team members; finding the culminating points of the musical work and building the logical development of its composition.&#x0D; The scientific novelty of the article is the description of innovative options for interaction with students in non-standard learning conditions aimed at maximum productivity and success.&#x0D; The practical significance of this research lies in the introduction of the proposed ideas into the educational process and the stimulation of creativity development and the use of creative pedagogical approach in communication with students.&#x0D; Conclusions. One of the main conclusions of this study is that online teaching of ensemble disciplines, in particular the quartet class, requires a professional, creative pedagogical approach which is highly integrated with knowledge of computer technologies, monitoring of new digital tools that simplify the educational process and make it possible to motivate students and get high learning results. This article represents a kind of impetus for the creative imagination of educators and is aimed at its further development.

Innovating musical composition through urban noise: A case study in experimental sound

The journey from concept to finished product is fascinating and intricate. It begins with a spark of inspiration, an idea that ignites the creative fire within. This concept serves as the foundation upon which the entire project is built. This research used a qualitative method with a case study approach. This research uses two types of data, including audio data of musical compositions and literature sources from articles and journals. The first step is to collect audio samples. This involves scouring libraries, recording sessions, and creating custom sounds to fit the project's vision. Each sample is carefully chosen for its timbre, texture, and emotional impact, which adds depth and richness to the final composition. The steps used are (1) audio data collection; (2) audio editing; (3) composing has four themes: exposition, development, recapitulation, and experimental; and (4) mixing and mastering, for blending all the elements of the track to create a polished and professional sound, and prepares the final blend for distribution, ensuring it sounds great on all playback systems. This involves applying EQ, compression, and limiting to maximize the loudness and clarity of the track.

Improving Generalization of Deepfake Detection With Data Farming and Few-Shot Learning

Recent advances in automated video and audio editing tools, generative adversarial networks (GANs), and social media allow creation and fast dissemination of high quality tampered videos, which are generally called deepfakes. Typically, in these videos, a face is swapped with someone else’s using GANs. Accessible open source software and apps for the face swapping led to a wide and rapid dissemination of the generated deepfakes, posing a significant technical challenge for their detection and filtering. In response to the threat, which deepfake videos can pose to our trust in video evidence, several large datasets of deepfake videos and several methods to detect them were proposed recently. However, the proposed methods suffer from a problem of overfitting on the training data and the lack of the generalization across different databases and the generative models. Therefore, in this paper, we investigate the techniques for improving the generalization of deepfake detection methods that can be employed in practical settings. We have selected two popular state of the art deepfake detectors: based on Xception and EfficientNet models, and we use five databases: from Google and Jigsaw, FaceForensics++, DeeperForensics, Celeb-DF, and our own publicly available large dataset DF-Mobio. To improve generalization, we apply different augmentation strategies used during training, including a proposed aggressive ‘data farming’ technique based on random patches. We also tested two few-shot tuning methods, when either a first convolutional layer or a last layer of a pre-trained model is tuned on 100 seconds from a training set of the test database. The experimental results clearly expose the generalization problem of deepfake detection methods, since the accuracy drops significantly when a model is trained on one dataset and evaluated on another. However, the silver lining is that an aggressive augmentation during training and a few-shot tuning on the test database can improve the accuracy of the detection methods in a cross-database scenario. As a side observation, we show the importance of database selection for training and evaluation, as FaceForensics++ is found to be better to use for training, while DeeperForensics is found to be significantly more challenging as a test database.

Elements of the methodology for teaching the theme "Creating and processing of sound information" using the free sound editor Audacity

The article presents the framework of the methodology for teaching the theme "Creating and processing of sound information" of the informatics course at the level of basic general education using the free cross-platform offline sound editor Audacity. The concept of "teaching methodology" refers to the process of transferring from the teacher to the student a certain necessary and sufficient set of algorithms for creating certain information objects that correspond to the information technology being studied. As a result of the analysis of possible software options to support the teaching of the theme under consideration in the informatics course, it is concluded that offline free cross-platform sound editors with low minimum system requirements is the best option. One of the most successful software options is the Audacity audio editor, which has a number of advantages over its counterparts. The article questions the principle of invariance of the method of teaching information technology, in particular technology for creating and processing sound information, with respect to the software and hardware used in the educational process, and substantiates the conclusion about the partial failure of this principle. A possible variant of the framework of the methodology for teaching the theme of the informatics course under consideration is given, which includes the division of the learning content into seven stages. Each of the stages includes a description of the presentation of the relevant educational material, including the technology for performing practical work aimed at mastering the basic elements of the functionality of the Audacity sound editor by students. The description of the author’s teaching methodology also contains the lesson planning corresponding to it on the theme " Creating and processing of sound information" of the informatics course for the basic school. The advantages of the proposed teaching methodology include the possibility of its use for both full-time and distance learning, as well as the low cost of its use in the educational process of a general education school. In addition, the methodology under consideration ensures a high resistance of the educational process to the destructive impact on the information structure of Russian educational organizations, which includes, among other things, an unmotivated refusal of licenses to use foreign-made proprietary software.

Video Editing: Technical Vs.Creative Tool

The audio and video editing software market are expected to increase at a growth rate (CAGR) of 11.24% as per the Technavio report by 2024 [1]. Video editing is the unique aspect of the filmmaking process that involves cutting and assembling segments of shot footage to create a cohesive story. Since its inception, video editing has transformed itself tremendously from a series of transition from kinetograph device (better as 'cutting and sticking ') used in early stage of editing to art of manipulating the viewers emotionally with the Kuleshov effect. Later came Non-linear video editing that could locate a frame within seconds and go back to the edit to change. Through this technical development, filmmakers have always understood video editing as a technical stream rather than the creative. In this research paper, the researcher tries to explore the technicality of video editing skills used in filmmaking since its inception. The paper also explores the extent to which the creative side of the video editing has been studied and understood.

Formant Measure of Indian English Vowels for Speaker Identity

With the growth of communication technology, reliability and security of communication devices became a challenging job. Voice biometrics are becoming increasingly popular as a promising alternative to traditional passwords to authenticate the user on devices for secure communication. Speech processing technology in voice identification may ensures and secure the user access over a range of systems, devices, and services. The formant frequency is the resonant frequency of the vocal cord. Frame-to-frame formants achieved using linear predictive coding (LPC) analysis technique by obtaining the tops of the envelopes. The source voice for vowel is a periodic signal in combination of fundamental frequency and a random noise generator generates unvoiced consonants. In this study, we used voice test samples of different male speakers from age 15 to 20 years. From each speaker utterance of different Indian English words, including vowels and consonants recorded using a digital audio editor software GoldWave v6.57. Formant frequency extracted from the spectrogram of recorded words using MATLAB 2016a signal processing toolbox. Finally, presented an approach for extracting vowels in the words spoken based on three formant frequencies such F1, F2 and F3. The results has shown the significance of vowels in Indian English words when formant frequency of vocal tract is considered.