Search

In this paper, an edit detection method for forensic audio analysis is proposed. It develops and improves a previous method through changes in the signal processing chain and a novel detection criterion. As with the original method, electrical network frequency (ENF) analysis is central to the novel edit detector, for it allows monitoring anomalous variations of the ENF related to audio edit events. Working in unsupervised manner, the edit detector compares the extent of ENF variations, centered at its nominal frequency, with a variable threshold that defines the upper limit for normal variations observed in unedited signals. The ENF variations caused by edits in the signal are likely to exceed the threshold providing a mechanism for their detection. The proposed method is evaluated in both qualitative and quantitative terms via two distinct annotated databases. Results are reported for originally noisy database signals as well as versions of them further degraded under controlled conditions. A comparative performance evaluation, in terms of equal error rate (EER) detection, reveals that, for one of the tested databases, an improvement from 7% to 4% EER is achieved, respectively, from the original to the new edit detection method. When the signals are amplitude clipped or corrupted by broadband background noise, the performance figures of the novel method follow the same profile of those of the original method.

In the first part of this study, the basic concepts of forensic phonetics such as voice, speech, and voice track are explained. In the second part; visual and auditory montage detection methods used in forensic phonetics, one of the lower branches of digital forensics, were examined. The most frequently used visual and auditory analysis methods have been determined by examining the literature. Then detailed information was given about them. Sound is a wave movement that creates a feeling of hearing in the ear by vibrating the molecules with a certain frequency and intensity with the movement of an object. The human voice has many unique features that called voice-print. Voice-print is frequently used in forensic phonetics to illuminate the crime. Voice is a reliable evidence used to detect guilt or detect a criminal. There are software that can do autonomous audio analysis. In addition, statistical and mathematical methods, artificial intelligence methods can be used. Visual and auditory analysis are performed on the sound and then evaluation is made according to different criteria. The success rate in speaker recognition methods is 85%–99%. Generally, the rate of misrecognition is 3% and the rate of non-recognition is 10%.

Many machine learning tasks have been shown solvable with impressive levels of success given large amounts of training data and computational power. For the problems which lack data sufficient to achieve high performance, methods for transfer learning can be applied. These refer to performing the new task while having prior knowledge of the nature of the data, gained by first performing a different task, for which training data is abundant. Shown successful for other machine learning tasks, transfer learning is now investigated in audio analysis. We propose to solve the weakly labelled problem of sound event tagging with small amounts of training data by transferring the abstract knowledge about the nature of audio data from another tagging task. The proposed methods constitute pre-training of a recurrent neural network or its parts to perform one tagging task given abundant and diverse training data, and then using it or its parts for a new task of tagging sound events of different nature, for which the data is limited. Several architectures for such transfer are proposed and evaluated, showing impressive classification accuracy of 83.4% with gains of up to 20 percentage points over the baseline given as little as 36 training samples for the target task.

While video analysis has become a standard feature of many security cameras, built audioanalytics remains relatively rare, despite the presence of both the audio channels in the devices and the available computing power to process audio data. However, audioanalytics has certain advantages over video analytics: microphones and maintenance cost is significantly less expensive than cameras; when the system is in real-time audio data stream is substantially less in volume than the flow of data from the video cameras, which imposes more loyal to the bandwidth requirements of data transmission channel. Audioanalytics systems can be especially in demand for urban surveillance, where you can automatically start to broadcast live video on the police control from the place of explosion and fire. Audioanalytics technology can also be used in the study and recording of certain events. In this study, we consider methods to identify audio event recognition, create a surveillance model using audioanalyitics methods and identify audio events by experiments.

International audience; As part of the 2016 public evaluation challenge on Detection and Classification of Acoustic Scenes and Events (DCASE 2016), the second task focused on evaluating sound event detection systems using synthetic mixtures of office sounds. This task, which follows the `Event Detection - Office Synthetic' task of DCASE 2013, studies the behaviour of tested algorithms when facing controlled levels of audio complexity with respect to background noise and polyphony/density, with the added benefit of a very accurate ground truth. This paper presents the task formulation, evaluation metrics, submitted systems, and provides a statistical analysis of the results achieved, with respect to various aspects of the evaluation dataset.

In this paper, we propose a framework for automated assessment of participation in classroom or professional meeting discussions using audio analysis. Participation is key to the success of businesses and schools; therefore, these establishments aim to measure, incentivise, and ultimately increase it. Currently, the assessment process is mostly subjective. The meeting chair or the teacher makes a subjective judgement on the level of participation by relying on memory or on recorded notes. The unreliability of this approach creates the need to propose objective tools through automation. We propose a collaborative framework using smart phones to capture multiple audio recordings of the meeting and merge them into a single audio-enhanced recording, offsetting audio volume differences in individual recordings due to varied distance from speakers. We use speech diarisation and speaker identification to segment the enhanced audio signal and recognise the identity of the participants in the discussion. We calculate participation statistics as percentages and present them to the discussion participants in graphical form, which helps keep the level balanced between participants. Our results validate the usefulness and potential of our framework in objectively estimating the participation level. The proposed framework is useful as a learning assessment tool and opens the door to automating minute taking when integrating speech recognition.

The aim of this paper was to discover what combination of audio features gives the best performance with music emotion detection. In our approach, emotion recognition was treated as a regression problem and a two-dimensional valence-arousal model was used to measure emotions in music. We used features extracted by Essentia and Marsyas, tools for audio analysis and audio-based music information retrieval. We examined the influence of different feature sets - low-level, rhythm, tonal, and their combination - on arousal and valence prediction. The use of a combination of different types of features significantly improves the results compared with using just one group of features. We found and presented features particularly dedicated to the detection of arousal and valence separately, as well as features useful in both cases.

3D video is introducing great changes in many health related areas. The realism of such information provides health professionals with strong evidence analysis tools to facilitate clinical decision processes. Speech and language therapy aims to help subjects in correcting several disorders. The assessment of the patient by the speech and language therapist (SLT), requires several visual and audio analysis procedures that can interfere with the patient's production of speech. In this context, the main contribution of this paper is a 3D video system to improve health information management processes in speech and language therapy. The 3D video retrieval and management system supports multimodal health records and provides the SLTs with tools to support their work in many ways: (i) it allows SLTs to easily maintain a database of patients' orofacial and speech exercises; (ii) supports three-dimensional orofacial measurement and analysis in a non-intrusive way; and (iii) search patient speech-exercises by similar facial characteristics, using facial image analysis techniques. The second contribution is a dataset with 3D videos of patients performing orofacial speech exercises. The whole system was evaluated successfully in a user study involving 22 SLTs. The user study illustrated the importance of the retrieval by similar orofacial speech exercise. info:eu-repo/semantics/publishedVersion

We present a complete, fully functional energy-autonomous audio sensor node with 6×5×4mm3 form factor. The system uses a new audio processing IC integrated with a MEMS microphone, general purpose 32-bit processor, 8Mb Flash, RF transceiver with custom 3D antenna, PV cells for energy harvesting and battery. The 4.7μW audio processing IC performs audio acquisition with 4–32× compression. The complete stand-alone system achieves 38mins of speech recording and energy-autonomous operation in room light.

The modified transmission-line implementation, like the low-pass filter version, is an active system, with adjustments to the filter Q values changing the filter shapes and gains. … This functional variation of Q with level gives a nearly uniform 2.5:1 compression ratio in the cochlear output for inputs ranging from 0 to 100 dB SPL. —“Accurate Tuning Curves In a Cochlear Model,” James Kates (1993a) The multiple-output cascade of asymmetric resonators with fast-acting compression (CARFAC) model of the auditory periphery combines concepts from many of the previous chapters, toward the primary goal of providing an efficient sound analyzer to support machine hearing applications. An important secondary goal of CARFAC is to connect closely enough with known auditory physiology and psychophysics that it can be used to visualize and explain many interesting auditory phenomena. It is not a goal to be physically accurate, well calibrated, or in agreement with every detail of peripheral auditory processing, though it can be used as a starting point for those who have such goals. Other than my own recent work (Lyon et al., 2010b; Lyon, 2010; Lyon et al., 2010a; Lyon, 2011b,a), the closest digital cochlear models in the literature to CARFAC are the variable- Q cascade–parallel models described by Kates (1993a), which also used cascades of asymmetric resonators specified by their poles and zeros; see the opening chapter quote above. The difference is that his stages include a second filter at each tap, and use a rather different pole–zero pattern, motivated by matching iso-rate neural tuning curves; ours is motivated by matching both psychophysical filters and physiological impulse responses, as discussed in Chapter 13. Putting the Pieces Together The CARFAC cochlear model pulls together the bits of knowledge that we surveyed in the previous nine chapters. The coupled-form asymmetric resonators from Chapter 8 are combined into a filterbank with gammatone-like response as described in Chapter 9, using the cascade architecture motivated by Chapter 12.

As multicore computers become widespread, the need for software programmers to decide on the most effective parallelization techniques becomes very prominent. In this case study, we examined a competition in which four teams of graduate students parallelized two sequential audio analysis applications. The students were introduced with PThreads, OpenMP and TBB parallel programming models. Use of different profiling and debugging tools was also taught during this course. Two of the teams parallelized libVorbis audio encoder and the other two parallelized the LAME encoding engine. The strategies used by the four teams to parallelize these applications included the use of taught programming models, focusing on both fine-grained and coarse-grained parallelism. These strategies are discussed in detail along with the tools utilized for the development and profiling. An analysis of the results obtained is also performed to discuss speedups and audio quality of the encoded output. A list of the lessons to be remembered while parallelizing an application has been provided as well. These lessons include best pedagogical methods, importance of understanding the program before choosing a programming model, concentrating on coarse-grained parallelism first, looking for dependency relaxation, parallelism beyond the predefined language constructs, the need of practice or prior experience in parallel programming and the need for assisting tools in parallelization.

In the current scenario, there exist huge amount of audio files with mixed sound sources. These mixed sounds consist of different frequencies viz. high frequency (string instruments like guitar), low frequencies (base instrument like drums, tabla) and intermediate human speech frequency. All these frequencies makes a music signal which is required for pleasure. The music creation is achieved by mixing of multiple signals using mixer. Our aim is to reverse the process of mixing and extract an audio signals so that they can be used in applications like karaoke, remix, instrumental music, audio restoration etc. One of the major application is noise cancellation and music transcription. In this paper we have demonstrated separation of single channel separation from mixed audio signal with the accuracy of 93% and average extraction speed of 20 seconds per minute of audio.

While humans can act as effective sensors, human input is subject to a high degree of error and highly dependent on the context. Furthermore, extracting the signal from the noise for social sensing is a difficult challenge. One approach to improving the accuracy of social sensing is to use physical sensors as a control knob for social sensing algorithms. In this paper, we present an architecture for using audio sensors as a way to control an algorithm used for social sensing of interesting events. We present various use cases where the architecture is applicable, and go into the details of one specific use case, namely using crowd behavior in a golf-course to identify and control social media feeds related to the course.

Speaker gender identification is considered among the most important tools in several multimedia applications namely in automatic speech recognition, interactive voice response systems and audio browsing systems. Gender identification systems performance is closely linked to the selected feature set and the employed classification model. Typical techniques are based on selecting the best performing classification method or searching optimum tuning of one classifier parameters through experimentation. In this paper, we consider a relevant and rich set of features involving pitch, MFCCs as well as other temporal and frequency-domain descriptors. Five classification models including decision tree, discriminant analysis, nave Bayes, support vector machine and k-nearest neighbor was experimented. The three best perming classifiers among the five ones will contribute by majority voting between their scores. Experimentations were performed on three different datasets spoken in three languages: English, German and Arabic in order to validate language independency of the proposed scheme. Results confirm that the presented system has reached a satisfying accuracy rate and promising classification performance thanks to the discriminating abilities and diversity of the used features combined with mid-level statistics.

During routine sleep diagnostic procedure, sleep is broadly divided into three states: rapid eye movement (REM), non-REM (NREM) states, and wake, frequently named macro-sleep stages (MSS). In this study, we present a pioneering attempt for MSS detection using full night audio analysis. Our working hypothesis is that there might be differences in sound properties within each MSS due to breathing efforts (or snores) and body movements in bed. In this study, audio signals of 35 patients referred to a sleep laboratory were recorded and analyzed. An additional 178 subjects were used to train a probabilistic time-series model for MSS staging across the night. The audio-based system was validated on 20 out of the 35 subjects. System accuracy for estimating (detecting) epoch-by-epoch wake/REM/NREM states for a given subject is 74% (69% for wake, 54% for REM, and 79% NREM). Mean error (absolute difference) was 36±34 min for detecting total sleep time, 17±21 min for sleep latency, 5±5% for sleep efficiency, and 7±5% for REM percentage. These encouraging results indicate that audio-based analysis can provide a simple and comfortable alternative method for ambulatory evaluation of sleep and its disorders.

Perceiving when, where and how a robot is touched is an important aspect towards a natural Human-Robot Interaction (HRI). To date, several technologies are used in Social Robotics to determine the area where a touch is performed, in some cases using many sensors. Moreover, most approaches do not tackle the kind of touch performed. In this paper, we introduce a novel technique based on audio analysis, and machine learning techniques. This presents a proof of concept aimed to provide some advantages regarding the state-of-the-art touch technologies for HRI: cost-efficiency since only a few microphones can cover the robot shell completely; robustness as microphones are not affected by electromagnetic interference or by external sounds; and accuracy taking into account the preliminary results.

Continuous Condition Monitoring of the machine is importan to improve efficiency of the machine, to avoid unexpected accidents and financial losses. Condition monitoring using audio signal processing is focused in this paper. The sound of the machine carries information about the machine condition. The change in features of audio signal are observed using the Peak Variation Response (PVR) of the Fast Fourier Transform (FFT) of signal. In this paper, the conventional FFT method has been used to prove that, it is sufficient for the detection of abnormalities due to different loading condition of the machine using audio signature. And a study on PVR of Intrinsic Mode Function (IMF) has been carried out to present the cause of variation in the energy and frequency of the oscillations of audio frequency (AF) modulated signals.

A command-line tool and Python framework is proposed for the exploration of a new form of audio synthesis known as ‘concatenative synthesis’, a form of synthesis that uses perceptual audio analyses to arrange small segments of audio based on their characteristics. The tool is designed to synthesise representations of an input target sound using a source database of sounds. This involves the segmentation and analysis of both the input sound and database, the matching of input segments to their closest segment from the database, and the resynthesis of the closest matches to produce the final result.\ud The project aims to provide a tool capable of generating high-quality sonic representations of an input, to present a variety of examples that demonstrated the breadth of possibilities that this style of synthesis has to offer and to provide a robust framework on which concatenative synthesis projects can be developed easily. The purpose of this project was primarily to highlight the potential for further development in the area of concatenative synthesis, and to provide a simple and intuitive tool that could be used by composers for sound design and experimentation. The breadth of possibilities for creating new sounds offered by this method of synthesis makes it ideal for digital sound design and electroacoustic composition.\ud Results demonstrate the wide variety of sounds that can be produced using this method of synthesis. A number of technical issues are outlined that impeded the overall quality of results and efficiency of the software. However, the project clearly demonstrates the strong potential for this type of synthesis to be used for creative purposes.

There is an emerging requirement in all modern Command & Control, Surveillance Systems for focusing on the capability of ‘Data Analysis’, besides ‘Data Processing’. This means that the modern Command & Control Information Systems are required to be capable of understanding each piece of huge data they receive, interpreting them and extracting the meaningful information for processing and presentation to the user. In this paper, we have discussed the role of Analytics, particularly in the field of Image, Text, and Audio Analysis, in military Surveillance and Command & Control Systems. We have also discussed the basic processes involved in these analytic engines. We have presented a generic framework for development of Image & Text Analytic Engines based on military context and knowledge base for an integrated surveillance system for military application.

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. This research work is partially supported by the Vicerrectorado de Investigación, Desarrollo e Innovación de la Universidad de Alicante through FPU program (UAFPU2014–5883) and the Spanish Ministerio de Economía y Competitividad through the TIMuL project (No. TIN2013–48152–C2–1–R, supported by EU FEDER funds).

A framework that utilizes audio information for recognition of activities of daily living (ADLs) in the context of a health monitoring environment is presented in this chapter. We propose integrating a Raspberry PI single-board PC that is used both as an audio acquisition and analysis unit. So Raspberry PI captures audio samples from the attached microphone device and executes a set of real-time feature extraction and classification procedures, in order to provide continuous and online audio event recognition to the end user. Furthermore, a practical workflow is presented, that helps the technicians that setup the device to perform a fast, user-friendly and robust tuning and calibration procedure. As a result, the technician is capable of "training"' the device without any need for prior knowledge of machine learning techniques. The proposed system has been evaluated against a particular scenario that is rather important in the context of any healthcare monitoring system for the elder: In particular, we have focused on the "bathroom scenario" according to which, a Raspberry PI device equipped with a single microphone is used to monitor bathroom activity on a 24/7 basis in a privacy-aware manner, since no audio data is stored or transmitted. The presented experimental results prove that the proposed framework can be successfully used for audio event recognition tasks.

The adage that there is no data like more data is not new in affective computing; however, with recent advances in deep learning technologies, such as end-to-end learning, the need for extracting big data is greater than ever. Multimedia resources available on social media represent a wealth of data more than large enough to satisfy this need. However, an often prohibitive amount of effort has been required to source and label such instances. As a solution, we introduce Cost-efficient Audio-visual Acquisition via Social-media Small-world Targeting (CAS2 T) for efficient large-scale big data collection from online social media platforms. Our system is based on a unique combination of small-world modelling, unsupervised audio analysis, and semi-supervised active learning. Such an approach facilitates rapid training on entirely new tasks sourced in their entirety from social multimedia. We demonstrate the high capability of our methodology via collection of original datasets containing a range of naturalistic, in-the-wild examples of human behaviours.

This page proposed an audio indicator which designed by using C9014, LED by operational amplifier level indicator, the decimal count/distributor of CD4017. The experimental can control audibly neon and holiday lights through the signal. Input audio signal after C9014 composed of operational amplifier for power amplifier, the adjust potentiometer extraction amplification signal input voltage CD4017 distributors make its drive to count, then connect the LED display running situation of the circuit. This simple audio indicator just use only U1 and can produce two colors LED with the audio signal tandem come pursuit of the running effect, from LED display the running of the situation takes can understand the general audio signal. The variation in the audio and the frequency of the signal and the corresponding level size. In this light can achieve jump to change, slowly, atlas, lighting four forms, used in home, hotel, discos, theater, advertising and other fields, and a wide range of USES, rU1h life in a mode...

This paper presents a system of audio signal processing based on FPGA,the system uses audio codec chip LM4550 to A/D transform and D/A transform the input analog audio signal and output digital audio signal.Using FPGA as the high speed signal processor to realize volume adjustment and audio effect control,so it can output different style music.Meantime, the system designs a FFT computing module and control system of VGA display interface,to compute the digital audio signal which is A/D transformed,and real-time display the frequency spectrum of audio signal on VGA.

The audio directional system is a new kind of loudspeakers, which can project the audio signal into a specified area as a beam of light. In this paper, the basic principle and system components of the audio directional system are presented. Based “Berktay far-field solution”, the total harmonic distortion of the self-demodulated signals is discussed. In addition, the relative tests are made with the audio directional experimental equipment which is designed. After comparing the theoretical data with the experimental data, point out the disadvantages of self-demodulation theory.

There is important physiological and pathological information in heart sound, so the patients’ information can be obtained by detection of their heart sounds. In the hardware of the system, the heart sound sensor HKY06B is used to acquire the heart sound signal, and the DSP chip TMS320VC5416 is used to process the heart sound. De-noising based on wavelet and HHT and other technical are used in the process of heart sound. There are five steps in the system: acquisition, de-noising, segmentation, feature extraction, and finally, heart sounds are classified

This article draws on the author's experience using qualitative video and audio analysis, most notably through use of the Transana qualitative video and audio analysis software program, as an alternative method for teaching IQ administration skills to students in a graduate psychology program. Qualitative video and audio analysis may be useful for psychology programs to more effectively and efficiently train students on IQ administration. Through use of Transana, video and audio footage and corresponding verbal and nonverbal transcripts of student-conducted IQ administrations can be coded and organized and later retrieved by any combination of codes, file or clip identifiers, or collections of clips and presented as a simultaneous, running display of video, audio, and corresponding transcripts that facilitates rich analysis and feedback.

Traditionally, the development and validation of computational measures of rhythmic similarity in music relies on proxy classification tasks, often equating rhythm similarity to genre. In this paper, we perform a comprehensive, cross-disciplinary exploration of the classification performance of a state-of-the-art system for rhythm similarity. By synthesizing the methods of quantitative analysis with a musicological perspective, detailed insight is gained into the various facets that affect system behaviour, consisting of three main areas: rhythmic sensitivities of a given feature representation, idiosyncrasies of the data used for evaluation, and the tenuous relationship between rhythmic similarity and genre. Through this study, we provide perspective on gauging the abilities of a computational system beyond classification accuracy, as well as a deeper understanding of system design and evaluation methodology as a musically meaningful exercise.

In this paper, we present a probabilistic framework for the simultaneous estimation of chords and keys from audio. The framework is formulated in terms of acoustic models for both keys and chords, and a prior model that contains musicological knowledge about chords and keys. The latter consists of a compound of four components: a duration and a change model for both keys and chords. This division allows us to modify each of the components separately and to choose the most appropriate sources of knowledge for each of them. Furthermore, this makes it easier to interpret their role and their relevance in the estimation procedure. We compared multiple configurations of our system, increasing in complexity. This has permitted us to explore the relation between keys and chords, and the importance of integrating prior musicological knowledge into an automatic estimation system. It was found that chord estimation scores mostly depend on the integration of durational knowledge, while key estimation also requires p...

Modulation frequency analysis has been studied predominantly in research areas such as communications, filtering and coding of digital signals, and representations of neurons in the biomedical field. In turn, modulation frequency features have surfaced in the area of music data mining, also known as music information retrieval (MIR). The term ‘modulation spectral features’ has been used rather loosely, but we refer to them as temporal patterns in a signal that may be revealed via the modulation spectrum. This paper consists of a literature survey of modulation features in which we review the historical use of general modulation features along with evolving interest in exploring modulation spectral features for data mining in music signals. We also discuss challenges encountered in employing modulation spectral features with music signals and suggest new directions in this area. Lastly, we further exploit modulation spectral features by applying these motivated concepts, properties, and parameters ...

The real-time processing for the input analog audio signal, audio processing program is proposed based on DSP. The system use FFT algorithm as the core, first, the input analog audio signal is sampled and A/D conversion using TLV320AIC23, and then use high speed digital signal processor to make real-time processing for the signal. Theoretical and experimental results show that the system can meet the design requirements, it has the advantage of high real-time and simple structure. The system has a good application and reference value for the development and design of data collecting and remote monitoring.

We propose a new approach to detect and quantify the periodic structure of dynamical systems using topological methods. We propose to use delay-coordinate embedding as a tool to detect the presence of harmonic structures by using persistent homology for robust analysis of point clouds of delay-coordinate embeddings. To discover the proper delay, we propose an autocorrelation like (ACL) function of the signals, and apply the introduced topological approach to analyze breathing sound signals for wheeze detection. Experiments have been carried out to substantiate the capabilities of the proposed method.

Nowadays, much is known about the functions of the components of the human auditory system. Computational models of these components are widely accepted and recently inspired the work of researchers in pattern recognition and signal processing. In this work we present a novel filter, which we call COPE (Combination of Peaks of Energy), that is inspired by the way the sound waves are converted into neuronal firing activity on the auditory nerve. A COPE filter creates a model of the pattern of the neural activity generated by a sound of interest and is able to detect the same pattern and modified versions of it. We apply the proposed method on the task of event detection for surveillance of roads. For the experiments, we use a publicly available data set, namely the MIVIA road events data set. The results that we achieve (recognition rate equal to \(94\%\) and false positive rate lower than \(4\%\)) and the comparison with existing methods demonstrate the effectiveness of the proposed bio-inspired filters for audio analysis.

The steelpan is an instrument with unique acoustic properties that allow for a wide range of timbral possibilities influenced by the choice of actuator. It is increasingly common for composers and performers to experiment with mallets made from a variety of materials that produce highly differentiated timbres. Examples of mallet types include wood and aluminum shafts covered with rubber tips, chopsticks, dowel rods, and cardboard tubes. Understanding how mallets interact with the steelpan is an important aspect of performance practice. Aside from standard rubber tipped mallets, most other mallets types are homemade and these characterizations will inform mallet design and construction in order to achieve the desired timbral result. While there have been studies analyzing the modes of vibrations of steelpan notes, the interactions between mallets and timbre hasn’t yet been studied and characterized. The goal of this work is to measure and characterize the timbral influence of a wide variety of mallets on high voiced steelpans through low level audio analysis with a focus on spectral features. Audio recordings were made with more than a dozen different mallets and several steelpans of three different types: tenor, double seconds, and double tenors.

In audio engineering, early reflection patterns are not usually variable, such as the user makes a selection from a handful of stored patterns simulating various rooms, halls, chambers and plates, or small room ambience, reflections is variable. To create digital reverb is much more complicated than combining a few digital relay units. The greater the spacing the larger the room sounds. Some difficult problems happened in recording situation is that every acoustic instrument engineers record sounds small or dry because their recording room does not have the same degree and circumstances of acoustic ambience as good as concert halls or venues. As a matter of fact that the same situation is also true of the most professional studios, apart from those with large, live rooms, and most pop music is recorded dry enough, either in a dry environment. In that case, people use close miking technique to get right sound source. Electronic effects units are used to recreate the desired ambience, and by far the most important effects unit of them all is reverberation.

An audio recording is subject to a number of possible distortions and artifacts. Consider, for example, artifacts due to acoustic reverberation and background noise. The acoustic reverberation depends on the shape and the composition of a room, and it causes temporal and spectral smearing of the recorded sound. The background noise, on the other hand, depends on the secondary audio source activities present in the evidentiary recording. Extraction of acoustic cues from an audio recording is an important but challenging task. Temporal changes in the estimated reverberation and background noise can be used for dynamic acoustic environment identification (AEI), audio forensics, and ballistic settings. We describe a statistical technique to model and estimate the amount of reverberation and background noise variance in an audio recording. An energy-based voice activity detection method is proposed for automatic decaying-tail-selection from an audio recording. Effectiveness of the proposed method is tested using a data set consisting of speech recordings. The performance of the proposed method is also evaluated for both speaker-dependent and speaker-independent scenarios.

In this paper we present a novel hybrid system that involves a formal method of automatic ontology generation for web-based audio signal processing applications. An ontology is seen as a knowledge management structure that represents domain knowledge in a machine interpretable format. It describes concepts and relationships within a particular domain, in our case, the domain of musical instruments. However, the different tasks of ontology engineering including manual annotation, hierarchical structuring and organization of data can be laborious and challenging. For these reasons, we investigate how the process of creating ontologies can be made less dependent on human supervision by exploring concept analysis techniques in a Semantic Web environment. In this study, various musical instruments, from wind to string families, are classified using timbre features extracted from audio. To obtain models of the analysed instrument recordings, we use K-means clustering to determine an optimised codebook of Line Spectral Frequencies (LSFs), or Mel-frequency Cepstral Coefficients (MFCCs). Two classification techniques based on Multi-Layer Perceptron (MLP) neural network and Support Vector Machines (SVM) were tested. Then, Formal Concept Analysis (FCA) is used to automatically build the hierarchical structure of musical instrument ontologies. Finally, the generated ontologies are expressed using the Ontology Web Language (OWL). System performance was evaluated under natural recording conditions using databases of isolated notes and melodic phrases. Analysis of Variance (ANOVA) were conducted with the feature and classifier attributes as independent variables and the musical instrument recognition F-measure as dependent variable. Based on these statistical analyses, a detailed comparison between musical instrument recognition models is made to investigate their effects on the automatic ontology generation system. The proposed system is general and also applicable to other research fields that are related to ontologies and the Semantic Web.

Recommending TV content to groups of viewers is best carried out when relevant information such as the demographics of the group is available. However, it can be difficult and time consuming to extract information for every user in the group. This paper shows how an audio analysis of the age and gender of a group of users watching the TV can be used for recommending a sequence of N short TV content items for the group. First, a state of the art audio-based classifier determines the age and gender of each user in an M-user group and creates a group profile. A genetic recommender algorithm then selects for each user in the profile, a single personalized multimedia item for viewing. When the number of items to be presented is different to the number of viewers in the group, i.e. M ≠ N, a novel adaptation algorithm is proposed that first converts the M-user group profile to an N-slot content profile, thus ensuring that items are proportionally allocated to users with respect to their demographic categorization. The proposed system is compared to an ideal system where the group demographics are provided explicitly. Results using real speaker utterances show that, in spite of the inaccuracies of state-of-the-art age-and-gender detection systems, the proposed system has a significant ability to predict an item with a matching age and gender category. User studies were conducted where subjects were asked to rate a sequence of advertisements, where half of the advertisements were randomly selected, and the other half were selected using the audio-derived demographics. The recommended advertisements received a significant higher median rating of 7.75, as opposed to 4.25 for the randomly selected advertisements 1. Recommending TV content to groups of viewers is best carried out when relevant information such as the demographics of the group is available. However, it can be difficult and time consuming to extract information for every user in the group. This paper shows how an audio analysis of the age and gender of a group of users watching the TV can be used for recommending a sequence of N short TV content items for the group. First, a state of the art audio-based classifier determines the age and gender of each user in an M-user group and creates a group profile. A genetic recommender algorithm then selects for each user in the profile, a single personalized multimedia item for viewing. When the number of items to be presented is different to the number of viewers in the group, i.e. M ≠ N, a novel adaptation algorithm is proposed that first converts the M-user group profile to an N-slot content profile, thus ensuring that items are proportionally allocated to users with respect to their demographic categorization. The proposed system is compared to an ideal system where the group demographics are provided explicitly. Results using real speaker utterances show that, in spite of the inaccuracies of state-of-the-art age-and-gender detection systems, the proposed system has a significant ability to predict an item with a matching age and gender category. User studies were conducted where subjects were asked to rate a sequence of advertisements, where half of the advertisements were randomly selected, and the other half were selected using the audio-derived demographics. The recommended advertisements received a significant higher median rating of 7.75, as opposed to 4.25 for the randomly selected advertisements 1.

Robustness against noise and interfering audio signals is one of the challenges in speech recognition and audio analysis technology. One avenue to approach this challenge is single-channel multiple-source modeling. Factorial hidden Markov models (FHMMs) are capable of modeling acoustic scenes with multiple sources interacting over time. While these models reach good performance on specific tasks, there are still serious limitations restricting the applicability in many domains. In this paper, we generalize these models and enhance their applicability. In particular, we develop an EM-like iterative adaptation framework which is capable to adapt the model parameters to the specific situation (e.g. actual speakers, gain, acoustic channel, etc.) using only speech mixture data. Currently, source-specific data is required to learn the model. Inference in FHMMs is an essential ingredient for adaptation. We develop efficient approaches based on observation likelihood pruning. Both adaptation and efficient inference are empirically evaluated for the task of multipitch tracking using the GRID corpus.

This paper introduces a Discrete Fourier Transform (DFT)-based algorithm to extract the Electric Network Frequency (ENF) information from an audio recording for use in audio authentication. The basic idea of the proposed algorithm is to calculate the specific spectral lines by DFT in the frequency domain at the desired frequency point instead of throughout the entire frequency band. Then a binary search technique is employed to search the next desired frequency bin to repeat the spectral line calculation until the hidden ENF information is extracted. The purpose is to improve the accuracy and precision of conventional ENF extraction methods and also to enhance the calculation efficiency. Both simulated audio signals with different signal-to-noise ratios (SNRs) and actual audio recordings are studied to verify the performance of the proposed algorithm. Two error-evaluation criteria, frequency offset and frequency bias, are defined to evaluate the algorithm performance on accuracy and precision. The test results and the error evaluation prove the validation and demonstrate the improvement of the proposed algorithm.

Audiovisual voice activity detection is a necessary stage in several problems, such as advanced teleconferencing, speech recognition, and human-computer interaction. Lip motion and audio analysis provide a large amount of information that can be integrated to produce more robust audiovisual voice activity detection (VAD) schemes, as we discuss in this paper. Lip motion is very useful for detecting the active speaker, and in this paper we introduce a new approach for lips and visual VAD. First, the algorithm performs skin segmentation to reduce the search area for lip extraction, and the most likely lip and non-lip regions are detected using a Bayesian approach within the delimited area. Lip motion is then detected using Hidden Markov Models (HMMs) that estimate the likely occurrence of active speech within a temporal window. Audio information is captured by an array of microphones, and the sound-based VAD is related to finding spatio-temporally coherent sound sources through another set of HMMs. To increase the robustness of the proposed system, a late fusion approach is employed to combine the result of each modality (audio and video). Our experimental results indicate that the proposed audiovisual approach presents better results when compared to existing VAD algorithms.

During the last two decades Red Palm Weevil (RPW, Rynchophorus Ferrugineus) has become one of the most dangerous threats to palm trees in many parts of the World. Its early detection is difficult, since palm trees do not show visual evidence of infection until it is too late for them to recover. For this reason the development of efficient early detection mechanisms is a critical element of RPW pest management systems. One of the early detection mechanisms proposed in the literature is based on acoustic monitoring, as the activity of RPW larvae inside the palm trunk is audible for human operators under acceptable environmental noise levels (rural areas, night periods, etc.). In this work we propose the design of an autonomous bioacoustic sensor that can be installed in every palm tree under study and is able to analyze the captured audio signal during large periods of time. The results of the audio analysis would be reported wirelessly to a control station, to be subsequently processed and conveniently stored. That control station is to be accessible via the Internet. It is programmed to send warning messages when predefined alarm thresholds are reached, thereby allowing supervisors to check on-line the status and evolution of the palm tree orchards. We have developed a bioacoustic sensor prototype and performed an extensive set of experiments to measure its detection capability, achieving average detection rates over 90%., We would like to acknowledge Michel Ferry and Susi Gomez (from Estacion Phoenix at Elche, Spain) for giving us access to their large RPW sound recording corpora and offering their cooperation during the development of this work. Finally, this work has been partially funded by Spanish Ministry of Education and Science under grants CTM2011-29691-C02-01, TIN2011-28435-C03-01 and TIN2011-27543-C03-03.

The use of a transparent thin film speaker in a home window can provide both an invisible audio playback device and an active noise cancellation system. However, several key challenges need to be addressed for development of such a system. A traditional feedforward active noise cancellation system uses direct microphone measurements for both reference and error signals. Such a system can degrade both the audio playback and the noise cancellation performance. Hence a wave separation algorithm is used in this paper for separation of the audio playback component from the external noise component for the reference signal. Further, an online adaptive secondary transfer function estimation method is used for accurate removal of the audio component from the error signal. Two approaches are attempted for the secondary transfer function estimation – use of source audio signals and use of additive white noise. The developed algorithms are evaluated in a scaled cabin equipped with a window and a transparent thin film actuator. Experimental results show that the developed system can preserve the auxiliary audio sound while cancelling external noise effectively. The system based on the use of source audio signals for secondary path estimation is found to yield the largest cancellation of external noise while producing the least amplitude of control inputs that cancel desired audio signals.

In this paper we propose an audio beat tracking system, IBT, for multiple applications. The proposed system integrates an automatic monitoring and state recovery mechanism, that applies (re-)inductions of tempo and beats, on a multi-agent-based beat tracking architecture. This system sequentially processes a continuous onset detection function while propagating parallel hypotheses of tempo and beats. Beats can be predicted in a causal or in a non-causal usage mode, which makes the system suitable for diverse applications. We evaluate the performance of the system in both modes on two application scenarios: standard (using a relatively large database of audio clips) and streaming (using long audio streams made up of concatenated clips). We show experimental evidence of the usefulness of the automatic monitoring and state recovery mechanism in the streaming scenario (i.e., improvements in beat tracking accuracy and reaction time). We also show that the system performs efficiently and at a level comparable to state-of-the-art algorithms in the standard scenario. IBT is multi-platform, open-source and freely available, and it includes plugins for different popular audio analysis, synthesis and visualization platforms.

This paper describes the design and development of RecApp, a mobile application for visualization and collaborative analysis of journalistic data from audio collections. We try to identify the challenges to support a team of journalists in understanding and analyzing mobile audio data constructing semantic networks from text by collaborative visualization approach.

We implemented media lifelog system with highlighting system with image analysis, video analysis and audio segmentation modules. Image analysis module has image classification, saliency region detection, face detection and facial expression recognition process. Video analysis module has cut detection and key frame detection process. And the result images of key frame detection is used as the input of image analysis module. Audio analysis module has audio segmentation process. ImageNet data is used for training and test database. The image classification accuracy is 83%. Automatic cut detection F1 score is 0.70. Cut detection F1 score is 0.80. Audio segmentation F score is 0.53. And facial expression recognition precision rate is 94.8% at 0.756 sec on a mobile phone.

A audio compressor is an important part of a audio processing system. The compression algorithm designed in this paper will be applied to audio compressor in the digital audio broadcasting transmitter. In this paper, an effective algorithm for dynamic control of the gain by taking mean square value is proposed, and two different audio signal from two channel processing schemes will be compared to get better one on the impact of compression. Then the algorithm is evaluated by the effect of compression of signal amplitude in the MATLAB simulation, and a scheme selected that signal is firstly dealt with to enhance the effect of the dual channel stereo and then is compressed is more suitable for the two channel audio compression from two schemes.

We propose a design of visible light communication which is based on the white LED power source. The design possesses effective software flowchart and the optimized circuit of the hardware modules which include power supply, signal amplification, LED driver, Audio signal transmission, Audio signal reception, filter and amplifier and Audio output. The testing of the design shows our system can realize the short-distance transmission of MP3 audio signal. Due to the advantages of stable performance, little distortion, low cast, simplicity and feasibility, our design owns a strong practical significance in the promotion of visible light communication technology.

In this paper, we present madmom, an open-source audio processing and music information retrieval (MIR) library written in Python. madmom features a concise, NumPy-compatible, object oriented design with simple calling conventions and sensible default values for all parameters, which facilitates fast prototyping of MIR applications. Prototypes can be seamlessly converted into callable processing pipelines through madmom's concept of Processors, callable objects that run transparently on multiple cores. Processors can also be serialised, saved, and re-run to allow results to be easily reproduced anywhere. Apart from low-level audio processing, madmom puts emphasis on musically meaningful high-level features. Many of these incorporate machine learning techniques and madmom provides a module that implements some in MIR commonly used methods such as hidden Markov models and neural networks. Additionally, madmom comes with several state-of-the-art MIR algorithms for onset detection, beat, downbeat and meter tracking, tempo estimation, and piano transcription. These can easily be incorporated into bigger MIR systems or run as stand-alone programs.