Search

Microphone identification is a crucial challenge in the field of digital audio forensics. The ability to accurately identify the type of microphone used to record a piece of audio can provide important information for forensic analysis and crime investigations. In recent years, transformer-based deep-learning models have been shown to be effective in many different tasks. This paper proposes a system based on a transformer for microphone identification based on recorded audio. Two types of experiments were conducted: one to identify the model of the microphones and another in which identical microphones were identified within the same model. Furthermore, extensive experiments were performed to study the effects of different input types and sub-band frequencies on system accuracy. The proposed system is evaluated on the Audio Forensic Dataset for Digital Multimedia Forensics (AF-DB). The experimental results demonstrate that our model achieves state-of-the-art accuracy for inter-model and intra-model microphone classification with 5-fold cross-validation.

We introduce a method for computer-assisted analysis of orchestration. We also look into the role that texture and orchestration have in structuring musical form. The method comprises a numerical representation, a hierarchy of ‘textural situations’ and measures for heterogeneity, diversity and complexity of orchestral-textural configurations. [ABSTRACT FROM AUTHOR]

Background: Respiratory sounds have been recognized as a possible indicator of behavior and health. Computer analysis of these sounds can indicate characteristic sound changes caused by COVID-19 and can be used for diagnostics of this illness. Objective: The aim of the study is to develop 2 fast, remote computer-assisted diagnostic methods for specific acoustic phenomena associated with COVID-19 based on analysis of respiratory sounds. Methods: Fast Fourier transform (FFT) was applied for computer analysis of respiratory sound recordings produced by hospital doctors near the mouths of 14 patients with COVID-19 (aged 18-80 years) and 17 healthy volunteers (aged 5-48 years). Recordings for 30 patients and 26 healthy persons (aged 11-67 years, 34, 60%, women), who agreed to be tested at home, were made by the individuals themselves using a mobile telephone; the records were passed for analysis using WhatsApp. For hospitalized patients, the illness was diagnosed using a set of medical methods; for outpatients, polymerase chain reaction (PCR) was used. The sampling rate of the recordings was from 44 to 96 kHz. Unlike usual computer-assisted diagnostic methods for illnesses based on respiratory sound analysis, we proposed to test the high-frequency part of the FFT spectrum (2000-6000 Hz). Results: Comparing the FFT spectra of the respiratory sounds of patients and volunteers, we developed 2 computer-assisted methods of COVID-19 diagnostics and determined numerical healthy-ill criteria. These criteria were independent of gender and age of the tested person. Conclusions: The 2 proposed computer-assisted diagnostic methods, based on the analysis of the respiratory sound FFT spectra of patients and volunteers, allow one to automatically diagnose specific acoustic phenomena associated with COVID-19 with sufficiently high diagnostic values. These methods can be applied to develop noninvasive screening self-testing kits for COVID-19. [ABSTRACT FROM AUTHOR]

Copyright of Coal Science & Technology (0253-2336) is the property of Coal Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This text describes the musical evaluation of a hybrid music notation system that combines traditional notation with symbols and concepts from spectromorphological analysis. During three academic years from 2017 to 2020, three groups of composition students learned to work with sound notation, recreating and interpreting short electroacoustic music sketches based solely on their notation transcriptions – they had not heard the original sketches. The students' score interpretations bore obvious similarities to the original music sketches and their written reflections showed that there were no major difficulties in understanding the notation although some difficulties existed concerning finding suitable sounds, especially sounds with stable pitch. [ABSTRACT FROM AUTHOR]

The quantitative assessment of the musical timbre in an audio record is still an open-ended issue. Evaluating the musical timbre allows not only to establish precise musical parameters but also the recognition, classification of musical instruments, and assessment of the musical quality of a sound record. In this paper, we present a minimum set of dimensionless descriptors, motivated by musical acoustics, using the spectra obtained by the Fast Fourier Transform (FFT), which allows describing the timbre of wooden aerophones (Bassoon, Clarinet, Transverse Flute, and Oboe) using individual sound recordings of the musical tempered scale. We postulate that the proposed descriptors are sufficient to describe the timbral characteristics in the aerophones studied, allowing their recognition using the acoustic spectral signature. We believe that this approach can be further extended to use multidimensional unsupervised machine learning techniques, such as clustering, to obtain new insights into timbre characterization. [ABSTRACT FROM AUTHOR]

Barking and other dog vocalizations have acoustic properties related to emotions, physiological reactions, attitudes, or some particular internal states. In the field of intelligent audio analysis, researchers use methods based on signal processing and machine learning to analyze the digitized acoustic signals' properties and obtain relevant information. The present work describes a method to classify the identity, breed, age, sex, and context associated with each bark. This information can support the decisions of people who regularly interact with animals, such as dog trainers, veterinarians, rescuers, police, people with visual impairment. Our approach uses deep neural networks to generate trained models for each classification task. We worked with 19,643 barks recorded from 113 dogs of different breeds, ages and sexes. Our methodology consists of three stages. First, the pre-processing stage prepares the data and transforms it into the appropriate format for each classification model. Second, the characterization stage evaluates different representation models to identify the most suitable for each task. Third, the classification stage trains each classification model and selects the best hyperparameters. After tuning and training each model, we evaluated its performance. We analyzed the most relevant features extracted from the audio and the most appropriate deep neural network architecture for that feature type. Even if the application of our method is not ready for being used in ethological practice, our evaluation showed an outstanding performance of the proposed method, surpassing previous research results on this topic, providing the basis for further technological development. • Analyzed diverse dog breed data, optimizing computational efficiency. • Largest variety & number of bark samples in barking classification. • Employed efficient characterization techniques, reducing computational cost. • Achieved classifier success with tailored deep neural network architecture. • Optimized classification with neural network hyperparameter tuning. [ABSTRACT FROM AUTHOR]

Identification of appropriate content-based features for the description of audio signals can provide a better repre-sentation of naturalistic music stimuli which, in recent years, have been used to understand how the human brain processes such information. In this work, an extensive clustering analysis has been carried out on a large and benchmark audio dataset to assess whether features commonly extracted in the literature are in fact statistically relevant. Our results show that not all of these well-known acoustic features might be statistically necessary. We also demonstrate quantitatively that, regardless of the musical genre, the same acoustic feature is selected to represent each cluster. This finding discloses that there is a general redundancy among the set of audio descriptors used, that does not depend on a particular music track or genre, allowing an expressive reduction of the number of features necessary to identify apropriate time instants on the audio for further brain signal processing of music stimuli. [ABSTRACT FROM AUTHOR]

Pain is a complex phenomenon, the experience of which varies widely across individuals. At worst, chronic pain can lead to anxiety and depression. Cost-effective strategies are urgently needed to improve the treatment of pain, and thus we propose a novel home-based pain measurement system for the longitudinal monitoring of pain experience and variation in different patients with chronic low back pain. The autonomous nervous system and audio-visual features are analyzed from heart rate signals, voice characteristics and facial expressions using a unique measurement protocol. Self-reporting is utilized for the follow-up of changes in pain intensity, induced by well-designed physical maneuvers, and for studying the consecutive trends in pain. We describe the study protocol, including hospital measurements and questionnaires and the implementation of the home measurement devices. We also present different methods for analyzing the multimodal data: electroencephalography, audio, video and heart rate. Our intention is to provide new insights using technical methodologies that will be beneficial in the future not only for patients with low back pain but also patients suffering from any chronic pain. [ABSTRACT FROM AUTHOR]

This work aims to demonstrate the feasibility that haptic information can be acquired from a da Vinci robotic tool using audio sensing according to sensor placement requirements in a real clinical scenario. For that, two potential audio sensor locations were studied using an experimental setup for performing, in a repeatable way, interactions of a da Vinci forceps with three different tissues. The obtained audio signals were assessed in terms of their resulting signal-to-noise-ratio (SNR) and their capability to distinguish between different tissues. A spectral energy distribution analysis using Discrete Wavelet Transformation was performed to extract signal signatures from the tested tissues. Results show that a high SNR was obtained in most of the audio recordings acquired from both studied positions. Additionally, evident spectral energy-related patterns could be extracted from the audio signals allowing us to distinguish between different palpated tissues.

Open-source software libraries have a significant impact on the development of Audio Signal Processing and Music Information Retrieval (MIR) systems. Despite the abundance of such tools, there is a lack of an extensive and easy-to-use reference library for audio feature extraction on Web clients. In this article, we present 'Essentia.js', an open-source JavaScript (JS) library for audio and music analysis on both web clients and JS engines. Along with the Web Audio API, it can be used for both offline and real-time audio feature extraction on web browsers. 'Essentia.js' is modular, lightweight, and easy-to-use, deploy, maintain, and integrate into the existing plethora of JS libraries and web technologies. It is powered by a WebAssembly back end cross-compiled from the Essentia C++ library, which facilitates a JS interface to a wide range of low-level and high-level audio features, including signal processing MIR algorithms as well as pre-trained TensorFlow.js machine learning models. It also provides a higher-level JS API and add-on MIR utility modules along with extensive documentation, usage examples, and tutorials. We benchmark the proposed library on two popular web browsers and the Node.js engine, and four devices, including mobile Android and iOS, comparing it to the native performance of Essentia and the Meyda JS library.

'Covering' previously recorded tracks is a central aspect of popular music. Despite an abundance of examples, discourse related to cover-version tracks is limited and includes questionable application of dichotomizing terminology ('cover', 'version') that can cause problems for interpreting the cover-version genre and diminish the nuanced approaches taken by artists who produce cover-versions. Examining recordings from the Punk Goes... album series reveals many examples that go beyond the either–or cover/version dichotomy generally presented in musicology. As such, this article has three main aims: to investigate the ways in which Punk Goes... tracks innovatively move between the poles of cover and version, thus requiring a new analytical framework; to explore the connection between imitation and transformation to the ascription of cover and version; and to move beyond prior musicological scholarship that emphasizes formal elements and composer intention. This article presents a reclassification of the terms 'cover' and 'version' as extreme poles of a 'cover-version spectrum' dependent on the listener's interpretation of the performative character. Analyses challenge assumptions that equate musical phrases with fixed musical meanings, suggesting instead that the interpreted manner of performance is more significant than syntactical concerns. This provides a structure for clearer examination of cover-versions and supports the view that semiotic methods are a vital tool in the analysis of recorded popular music. [ABSTRACT FROM AUTHOR]

Research on self-efficacy and confidence has spread across several subfields of psychology and neuroscience. The role of one’s confidence is very crucial in the formation of attitude and communication skills. The importance of differentiating the levels of confidence is quite visible in this domain. With the recent advances in extracting behavioral insight from a signal in multiple applications, detecting confidence is found to have great importance. One such prominent application is detecting confidence in interview conversations. We have collected an audiovisual data set of interview conversations with 34 candidates. Every response (from each of the candidate) of this data set is labeled with three levels of confidence: high, medium, and low. Furthermore, we have also developed algorithms to efficiently compute such behavioral confidence from speech and video. A deep learning architecture is proposed for detecting confidence levels (high, medium, and low) from an audiovisual clip recorded during an interview. The achieved unweighted average recall (UAR) reaches 85.9% on audio data and 73.6% on video data captured from an interview session.

Amidst discussions regarding the nature of a musical work, tensions within and between score- and performance-based approaches often increase ideological entrenchment. Opera's textual and visual elements, along with its inherently social nature, both simultaneously complicate understanding of a work's nature and provide interdisciplinary analytical inroads. Analysis of operatic performance faces challenges of how to interrogate onstage musical behaviors, and how they relate to both dramatic narrative and an opera's identity. This article applies Martin Heidegger's dichotomy of technē and poiēsis to relationships between scores, performances, and works, characterizing works as conceptual, and scores and performances as tangible embodiments. Opera scholarship relies primarily upon scores, creating a lacuna of sound-based examinations. Adapting analyses developed in CHARM's "Mazurka Project," this essay incorporates textual considerations into tempo hierarchy as a means of asserting each performance's nuanced uniqueness and thus provides a window into performers' creative processes. Interviews with the performers considered in this study confirmed postulations derived from analyzing temporal-textual emphases. This approach is adaptable to other expressive elements employed in creating a role onstage. In addition to the hybrid empirical-hermeneutic application, the datasets created in this approach could be valuable as ground truth in machine learning applications.

Vibrato is one of the most common musical techniques used for the enrichment of vocal and musical instrument sounds. We propose a method that can analyse the intonation, vibrato rate, and vibrato extent of a vibrato tone as a function of time, which is based on the discrete Fourier transform of its fundamental frequency trajectory. According to experimental results, the proposed method is robust to the irregularities in the fundamental frequency trajectory. In addition, the proposed method provides different results for intonation and vibrato extent from those of Prame's method when the fundamental frequency trajectory is not perfectly sinusoidal. [ABSTRACT FROM AUTHOR]

Purpose: Minimally invasive surgery (MIS) has become the standard for many surgical procedures as it minimizes trauma, reduces infection rates and shortens hospitalization. However, the manipulation of objects in the surgical workspace can be difficult due to the unintuitive handling of instruments and limited range of motion. Apart from the advantages of robot-assisted systems such as augmented view or improved dexterity, both robotic and MIS techniques introduce drawbacks such as limited haptic perception and their major reliance on visual perception. Methods: In order to address the above-mentioned limitations, a perception study was conducted to investigate whether the transmission of intra-abdominal acoustic signals can potentially improve the perception during MIS. To investigate whether these acoustic signals can be used as a basis for further automated analysis, a large audio data set capturing the application of electrosurgery on different types of porcine tissue was acquired. A sliding window technique was applied to compute log-mel-spectrograms, which were fed to a pre-trained convolutional neural network for feature extraction. A fully connected layer was trained on the intermediate feature representation to classify instrument–tissue interaction. Results: The perception study revealed that acoustic feedback has potential to improve the perception during MIS and to serve as a basis for further automated analysis. The proposed classification pipeline yielded excellent performance for four types of instrument–tissue interaction (muscle, fascia, liver and fatty tissue) and achieved top-1 accuracies of up to 89.9%. Moreover, our model is able to distinguish electrosurgical operation modes with an overall classification accuracy of 86.40%. Conclusion: Our proof-of-principle indicates great application potential for guidance systems in MIS, such as controlled tissue resection. Supported by a pilot perception study with surgeons, we believe that utilizing audio signals as an additional information channel has great potential to improve the surgical performance and to partly compensate the loss of haptic feedback. [ABSTRACT FROM AUTHOR]

• Analyze the students' behavior together with teaching contents and characteristic. • Focus on the ratio of students paying attention to the teaching contents. • Extract the teaching characteristic and topics from in-classroom videos. • Represent the teaching characteristic by extracting features from teacher's audio. • Analyze the students' behavior on different topics extracted from audio information. The automatic analysis of students' in-classroom behavior is valuable to evaluate the effect of teaching. Recent studies of in-classroom video analysis mainly focus on lecture content, positions and identities of students. In this paper, we propose to analyze the students' concentration degree to the teacher or teaching content. Specifically, we detect students' faces, track faces, and analyze the students' behavior, i.e. raising or downing faces and corresponding head orientations to the teacher, teaching content or not. Besides, texts are obtained from the teacher's speech and the course topics taught in the class are extracted. Audio features of the teacher's speech are extracted and analyzed. Finally, the correlation of the students' concentration degree with the course topics, audio features are analyzed. This analysis can help teachers find the effective teaching characteristic to better improve students' concentration degree. [ABSTRACT FROM AUTHOR]

Currently, VoIP company technicians conduct tests to classify call quality as good or bad. Even though, there are automatic platforms that make test VoIP calls to classify them, they do not perform audio processing to detect False Answer Supervision (FAS), which is a common and undesirable feature of VoIP calls. In this paper, a Vector Support Machine (SVM) along with several functions used in voice recognition were implemented to emulate the human decision procedure (the task of audio classification and analysis performed by technicians). The experiments were based on the comparison between the results obtained from the current classification methods and those derived from the SVM. A 10-fold cross-validation was used to evaluate the system performance. The tests results from the proposed methodology show a better percentage of successful classification compared to a selected automatic platform called CheckMyRoutes.

Abstract Onset detection still has room for improvement, especially when dealing with polyphonic music signals. For certain purposes in which the correctness of the result is a must, user intervention is hence required to correct the mistakes performed by the detection algorithm. In such interactive paradigm, the exactitude of the detection can be guaranteed at the expense of user’s work, being the effort required to accomplish the task, the value that has to be both quantified and reduced. The present work studies the idea of interactive onset detection and proposes a methodology for assessing the user’s workload, as well as a set of interactive schemes for reducing such workload when carrying out this detection task. Results show that the evaluation strategy proposed is able to quantitatively assess the invested user effort. Also, the presented interactive schemes significantly facilitate the correction task compared with the manual annotation.

Highlights • We introduce trainable COPE feature extractors for sound representation learning. • A COPE feature extractor is trained using a single prototype sound of interest. • We propose a method for audio event detection with robustness to varying SNR. • We experiment on four data sets: MIVIA audio, MIVIA roads, ESC-10 and TU Dortmund. • We achieve better results than existing methods for audio event detection. Abstract Sound analysis research has mainly been focused on speech and music processing. The deployed methodologies are not suitable for analysis of sounds with varying background noise, in many cases with very low signal-to-noise ratio (SNR). In this paper, we present a method for the detection of patterns of interest in audio signals. We propose novel trainable feature extractors, which we call COPE (Combination of Peaks of Energy). The structure of a COPE feature extractor is determined using a single prototype sound pattern in an automatic configuration process, which is a type of representation learning. We construct a set of COPE feature extractors, configured on a number of training patterns. Then we take their responses to build feature vectors that we use in combination with a classifier to detect and classify patterns of interest in audio signals. We carried out experiments on four public data sets: MIVIA audio events, MIVIA road events, ESC-10 and TU Dortmund data sets. The results that we achieved (recognition rate equal to 91.71% on the MIVIA audio events, 94% on the MIVIA road events, 81.25% on the ESC-10 and 94.27% on the TU Dortmund) demonstrate the effectiveness of the proposed method and are higher than the ones obtained by other existing approaches. The COPE feature extractors have high robustness to variations of SNR. Real-time performance is achieved even when the value of a large number of features is computed. [ABSTRACT FROM AUTHOR]

Autonomously generating artificial soundscapes for video games, virtual reality, and sound art presents several non-trivial challenges. We outline a system called Audio Metaphor that is built upon the notion that sound design for soundscape compositions is emotionally informed. We first define the problem space of generating soundscape compositions referencing the sound design and soundscape literature. Next, we survey the state-of-the-art soundscape generation systems and establish the characteristics and challenges for evaluating these types of systems. We then describe the Audio Metaphor system that aims to model the soundscape generation problem using a method of soundscape emotion recognition and segmentation based on perceptual classes, and an autonomous mixing engine utilising optimisation and prediction algorithms to generate a soundscape composition. We evaluate the soundscape compositions generated by Audio Metaphor by comparing them with those created by a human expert and also those generated randomly. Our analysis of the evaluation study reveals that the proposed soundscape generation model is human-competitive regarding semantic and emotion-based indicators. [ABSTRACT FROM AUTHOR]

Highlights • CNNs provide state-of-the-art results in speech-music discrimination. • Transfer learning can be used to transfer knowledge across different modalities. • CNNs & transfer-learning can significantly reduce the training data requirements. • Data augmentation and representation play important role when training audio-CNNs. Abstract Speech music discrimination is a traditional task in audio analytics, useful for a wide range of applications, such as automatic speech recognition and radio broadcast monitoring, that focuses on segmenting audio streams and classifying each segment as either speech or music. In this paper we investigate the capabilities of Convolutional Neural Networks (CNNs) with regards to the speech - music discrimination task. Instead of representing the audio content using handcrafted audio features, as traditional methods do, we use deep structures to learn visual feature dependencies as they appear on the spectrogram domain (i.e. train a CNN using audio spectrograms as input images). The main contribution of our work focuses on the potentials of using pre-trained deep architectures along with transfer-learning to train robust audio classifiers for the particular task of speech music discrimination. We highlight the supremacy of the proposed methods, compared both to the typical audio-based and deep-learning methods that adopt handcrafted features, and we evaluate our system in terms of classification success and run-time execution. To our knowledge this is the first work that investigates CNNs for the task of speech music discrimination and the first that exploits transfer learning across very different domains for audio modeling using deep-learning in general. In particular, we fine-tune a deep architecture originally trained for the Imagenet classification task, using a relatively small amount of data (almost 80 min of training audio samples) along with data augmentation. We evaluate our system through extensive experimentation against three different datasets. Firstly we experiment on a real-world dataset of more than 10 h of uninterrupted radio broadcasts and secondly, for comparison purposes, we evaluate our best method on two publicly available datasets that were designed specifically for the task of speech-music discrimination. Our results indicate that CNNs can significantly outperform current state-of-the-art in terms of performance especially when transfer learning is applied, in all three test-datasets. All the discussed methods, along with the whole experimental setup and the respective datasets, are openly provided for reproduction and further experimentation. [ABSTRACT FROM AUTHOR]

Speech accents can possess valuable information about the speaker, and can be used in intelligent multimedia-based human-computer interfaces. The performance of algorithms for automatic classification of accents is often evaluated using audio datasets that include recording samples of different people, representing different accents. Here we describe a method that can detect bias in accent datasets, and apply the method to two accent identification datasets to reveal the existence of dataset bias, meaning that the datasets can be classified with accuracy higher than random even if the tested algorithm has no ability to analyze speech accent. We used the datasets by separating one second of silence from the beginning of each audio sample, such that the one-second sample did not contain voice, and therefore no information about the accent. An audio classification method was then applied to the datasets of silent audio samples, and provided classification accuracy significantly higher than random. These results indicate that the performance of accent classification algorithms measured using some accent classification benchmarks can be biased, and can be driven by differences in the background noise rather than the auditory features of the accents.

Predictive Maintenance ( PdM ) has a main role in the Fourth Industrial Revolution; its goal is to design models that can safely detect failure in systems before they fail, aiming to reduce financial, environmental, and operational costs. A brushless DC (BLDC) electric motors have increasingly become more popular and been gaining popularity in industrial applications, so their analysis for PdM applications is only a natural progression; audio analysis proves to be a useful method to achieve this and rises as a very pragmatic case of study of the characteristics of the motors. The main goal of this paper is to showcase sound-based behavior of BLDC motors in different failure modes as result of an experiment led by researchers at Universidad del Cauca in Colombia. This dataset may provide researchers with useful information regarding signal processing and the development of Machine Learning applications that would achieve an improvement within Predictive Maintenance and I4.0.Predictive Maintenance ( PdM ) has a main role in the Fourth Industrial Revolution; its goal is to design models that can safely detect failure in systems before they fail, aiming to reduce financial, environmental, and operational costs. A brushless DC (BLDC) electric motors have increasingly become more popular and been gaining popularity in industrial applications, so their analysis for PdM applications is only a natural progression; audio analysis proves to be a useful method to achieve this and rises as a very pragmatic case of study of the characteristics of the motors. The main goal of this paper is to showcase sound-based behavior of BLDC motors in different failure modes as result of an experiment led by researchers at Universidad del Cauca in Colombia. This dataset may provide researchers with useful information regarding signal processing and the development of Machine Learning applications that would achieve an improvement within Predictive Maintenance and I4.0., (© 2023 The Author(s).)

This study deals with the strong relationship between emotions and music, investigating three main research questions: (RQ1) Are there differences in human music perception (e.g., emotions, tempo, instrumentation, and complexity), according to musical education, experience, demographics, and personality traits?; (RQ2) Do certain perceived music characteristics correlate (e.g., tension and sadness), irrespective of a particular listener's background or personality?; (RQ3) Does human perception of music characteristics, such as emotions and tempo, correlate with descriptors extracted from music audio signals? To investigate our research questions, we conducted two user studies focusing on different groups of subjects. We used web-based surveys to collect information about demographics, listening habits, musical education, personality, and perceptual ratings with respect to perceived emotions, tempo, complexity, and instrumentation for 15 segments of Beethoven's 3rdsymphony, “Eroica”. Our experiments showed that all three research questions can be affirmed, at least partly. We found strong support for RQ2 and RQ3, while RQ1 could be confirmed only for some perceptual aspects and user groups. [ABSTRACT FROM AUTHOR]

Purpose: To investigate the frequency, localizing significance, and intensity characteristics of ictal vocalization in different focal epilepsy syndromes.Methods: Up to four consecutive focal seizures were evaluated in 277 patients with lesional focal epilepsy, excluding isolated auras and subclinical EEG seizure patterns. Vocalization was considered to be present if observed in at least one of the analyzed seizures and not being of speech quality. Intensity features of ictal vocalization were analyzed in a subsample of 17 patients with temporal and 19 with extratemporal epilepsy syndrome.Results: Ictal vocalization was observed in 37% of the patients (102/277) with similar frequency amongst different focal epilepsy syndromes. Localizing significance was found for its co-occurrence with ictal automatisms, which identified patients with temporal seizure onset with a sensitivity of 92% and specificity of 70%. Quantitative analysis of vocalization intensity allowed to distinguish seizures of frontal from temporal lobe origin based on the intensity range (p = 0.0003), intensity variation (p < 0.0001), as well as the intensity increase rate at the beginning of the vocalization (p = 0.003), which were significantly higher in frontal lobe seizures. No significant difference was found for mean intensity and mean vocalization duration.Conclusions: Although ictal vocalization is similarly common in different focal epilepsies, it shows localizing significance when taken into account the co-occurring seizure semiology. It especially increases the localizing value of automatisms, predicting a temporal seizure onset with a sensitivity of 92% and specificity of 70%. Quantitative parameters of the intensity dynamic objectively distinguished frontal lobe seizures, establishing an observer independent tool for semiological seizure evaluation. [ABSTRACT FROM AUTHOR]

In the field of Automatic Music Transcription, note tracking systems constitute a key process in the overall success of the task as they compute the expected note-level abstraction out of a frame-based pitch activation representation. Despite its relevance, note tracking is most commonly performed using a set of hand-crafted rules adjusted in a manual fashion for the data at issue. In this regard, the present work introduces an approach based on machine learning, and more precisely supervised classification, that aims at automatically inferring such policies for the case of piano music. The idea is to segment each pitch band of a frame-based pitch activation into single instances which are subsequently classified as active or non-active note events. Results using a comprehensive set of supervised classification strategies on the MAPS piano data-set report its competitiveness against other commonly considered strategies for note tracking as well as an improvement of more than in terms of F-measure when compared to the baseline considered for both frame-level and note-level evaluations. [ABSTRACT FROM AUTHOR]

Accurate frequency tracking of harmonic signals is an essential process for analysis of musical instrument and singing sounds. For fine frequency estimation, we propose two methods for enhancement of the phase difference estimation (PDE). The first method is improved PDE that maximises the signal level at the frequency estimation position, which is effective especially at low signal-to-noise ratio (SNR). The second method is window switching that minimises the effects of harmonics by suppressing their sidelobe levels, which is effective at high SNR. Window switching is also applicable to existing fine frequency estimation methods as well as the PDE and improved PDE. Experimental results and application examples show that the proposed methods show meaningful improvements over the PDE and are effective for high-accuracy frequency analysis. The proposed methods can be adopted as a module for sound analysis and processing tools and software, which are expected to contribute to the comprehensive analysis of musical signals. [ABSTRACT FROM AUTHOR]