Search

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.

Many audio analysis systems employ peak picking procedure to produce the final decision. A typical scheme uses a thresholding function to minimise detection errors where its form depends on the structure of the input signal. The paper covers the problem of an adaptive thresholding function estimation. Using the genetic algorithm to optimise the components of the thresholding function we have determined the level of importance of individual local statistics on the final function representation. The proposed method has been used to tune the peak detection procedure to identify the change points in an audio signal. In the result of the heuristic configuration, the best accuracy of segment boundaries have been obtained for thresholding function built on top of two local statistics of the detection function and constant value. Finally, as an example, a comparison with the state–of–the–art scheme for audio segmentation was performed.

With the fast development of computer and information technology, multimedia data has become the most important form of information media. Auditory information plays an important role in information location, this comes from the fact that it can be difficult to find useful information. Thus audio classification becomes more important in audio analysis as it prepares for content-based audio retrieval. There is quite a bit of research on the topic of audio classification methods, audio feature analysis, and extraction based on audio classification. Many works of literature extract features of audio signals based on time or Fourier transform frequency domain. The emergence of the wavelet theory provides a time-frequency analysis tool for signal analysis. Wavelet transformation is a local transformation of the signal in time and frequency which can effectively extract information from the signal, and perform multi-scale refinement analysis on functions or signals through operations such as stretching and translation instead of the traditional Fourier transformation. In the time-frequency analysis of the signal, the wavelet analysis captures the local time and frequency characters of the signal which can improve the ability of signal analysis. It can also change certain locals of the signal without affecting other aspects of it. In this paper, the frequency domain features are combined with the wavelet domain features. At the same time that the MFCC features are extracted, the discrete wavelet transform is used to extract the features of the wavelet domain. Then the statistical features are extracted for each audio example, and the SVM model is used to realize the different forms of audio classification identification.

Η Ημιτονοειδής Μοντελοποίηση είναι μια από τις πιο ευρέως χρησιμοποιούμενες παραμετρικές μεθόδους για την επεξεργασία σήματος φωνής και ήχου. Η ακριβής εκτίμηση των ημιτονοειδών παραμέτρων (πλάτη, συχνότητες, και φάσεις) είναι ένα κρίσιμο σημείο για τη ακριβή αναπαράσταση των σημάτων που αναλύονται. Στην παρούσα εργασία, με βάση τις πρόσφατες εξελίξεις στην ημιτονοειδή ανάλυση, προτείνουμε υψηλής ανάλυσης, προσαρμόσιμα ημιτονοειδή μοντέλα για συστήματα ανάλυσης, σύνθεσης, και τροποποίησης ομιλίας. Στόχος μας είναι να προσφέρουμε συστήματα που αναπαριστούν σήματα φωνής με εξαιρετικά ακριβή και συμπαγή τρόπο.Εμπνευσμένοι από πρόσφατα προταθέντα μοντέλα, όπως το προσαρμόσιμο Σχεδον - Αρμονικό Μοντέλο (aQHM) και το προσαρμόσιμο Αρμονικό Μοντέλο (aHM), διατυπώνουμε τη θεωρία της προσαρμόσιμης Ημιτονοειδούς Μοντελοποίησης και προτείνουμε ένα μοντέλο που ονομάζεται εκτεταμένο προσαρμόσιμο Σχεδον - Αρμονικό Μοντέλο (eaQHM), το οποίο είναι ένα μη παραμετρικό μοντέλο, ικανό να προσαρμόσει τα στιγμιαία πλάτη και φάσεις των συναρτήσεων βάσης του στα τοπικά χρονικά μεταβαλλόμενα χαρακτηριστικά του σήματος της φωνής, αμβλύνοντας έτσι τη γνωστή υπόθεση της τοπικής στασιμότητας. Αποδεικνύεται ότι το eaQHM παρουσιάζει υψηλότερες επιδόσεις από το aQHM στην ανάλυση και ανασύνθεση των έμφωνων τμημάτων φωνής. Με βάση το eaQHM, ένα υβριδικό σύστημα ανάλυσης / σύνθεσης ομιλίας παρουσιάζεται (eaQHNM), μαζί με μια υβριδική έκδοση του του aHM (aHNM). Επιπλέον, παρουσιάζουμε κίνητρα για μια αναπαράσταση του σήματος της φωνής σε όλο το φάσμο και σε όλη τη διάρκεια του, χρησιμοποιώντας το eaQHM, αναπαριστώντας έτσι όλα τα μέρη του σήματος της φωνής, με υψηλής ανάλυσης AM-FM ημίτονα. Η αξιολόγηση δείχνει ότι η προσαρμοσιμότητα και η σχεδόν-αρμονικότητα είναι αρκετή για να παράξει πολύ υψηλή ποιότητα στην ανασύνθεση των άφωνων τμημάτων της φωνής. Στη συνέχεια, παρουσιάζεται το σύστημα πλήρους φάσματος ανάλυσης και σύνθεσης βασισμένο στο eaQHM, το οποίο υπερτερεί συστημάτων που θεωρούνται state-of-the-art, υβριδικά ή πλήρους ανάλυσης, στην ανάλυση και ανασύνθεση φωνής. Η υπεροχή του στην ποιότητα ανασύνθεσης επιβεβαιώθηκε με αντικειμενικές και υποκειμενικές αξιολογήσεις.Όσον αφορά τις εφαρμογές, το eaQHM και το aHM εφαρμόζονται σε μετασχηματισμούς φωνής (κλιμάκωση χρόνου και κλιμάκωση θεμελιώδους συχνότητας). Οι μετασχηματισμοί που προκύπτουν είναι υψηλής ποιότητας, ακολουθώντας πολύ απλούς κανόνες, σε σύγκριση με άλλα συστήματα state-of-the-art. Οι έννοιες της σχετικής φάσης και της καθυστέρησης σχετικής φάσης είναι ζωτικής σημασίας για την ανάπτυξη μετασχηματισμένου σήματος με χαρακτηριστικά αναλλοίωτου σχήματος, χωρίς τεχνικά ελαττώματα, και υψηλής ποιότητας. Τα αποτελέσματα δείχνουν ότι τα συστηματα βασισμένα στην αρμονικότητα προτιμούνται έναντι αυτών της σχεδόν-αρμονικότητας, λόγω της απλότητας της αναπραστάσης. Επιπλέον, το eaQHM εφαρμόζεται στο πρόβλημα της μοντελοποίησης σημάτων ήχου, και συγκεκριμένα ήχων μουσικών οργάνων. Το eaQHM αξιολογείται και σύγκρινεται με state-of-the-art συστήματα, και έχει υψηλές επιδόσεις όσον αφορά την ποιότητα επανασύνθεσης, αναπαριστωντας με επιτυχία τα στάδια της επίθεσης, της μετάβασης, και της στατικότητας ενός ήχου μουσικού οργάνου. Τέλος, μια άλλη προτεινόμενη εφαρμογή έγκειται στην ανάλυση και ταξινόμηση της εκφραστικής ομιλίας. Το eaQHM εφαρμόζεται στην ανάλυση της εκφραστικής ομιλίας, παρέχοντας τις στιγμιαίες παραμέτρους του ως χαρακτηριστικά που μπορούν να χρησιμοποιηθούν στην αναγνώριση και ταξινόμηση, βασισμένη σε διανυσματικούς κβαντιστές, εκφραστικής ομιλίας. Αν και τα ημιτονοειδή μοντέλα δεν χρησιμοποιούνται συνήθως σε τέτοιες εφαρμογές, τα αποτελέσματα είναι ελπιδοφόρα.

Music is one of the most pious cultures that exist throughout the world. Almost every country has their own rich musical culture, most of them are with strong classical backgrounds. India is one such land, rich in various types of music. This research paper is about the study of the identification of Raga. ‘Raga’ is said to be the melody of a song. We have used the Audio Signal Processing (ASP) techniques for feature extraction of two very similar ragas from Carnatic Music (CM) by analyzing the ‘RagaChhaya’ swaras commonly known as ‘RagaLakshna’ swaras of these ragas using Essentia and SMS tools. Essentia is an open-source library based on C++ with python and JavaScript wrappers for extensive audio analysis and MIR studies. The ‘SMS-tools’ is an application called ‘Spectral Modelling and Synthesis’ used to analyze sound and music applications. We proposed a supervised machine learning model trained with the features extracted from the two ragas considered, using the SMS-tools, for testing and training data that compares the given input piece of the audio signal to correctly identify based on the trained model.

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.

Low-level audio features are commonly used in many audio analysis tasks, such as audio scene classification or acoustic event detection. Due to the variable length of audio signals, it is a common approach to create fixed-length feature vectors consisting of a set of statistics that summarize the temporal variability of such short-term features. To avoid the loss of temporal information, the audio event can be divided into a set of mid-term segments or texture windows. However, such an approach requires to estimate accurately the onset and offset times of the audio events in order to obtain a robust mid-term statistical description of their temporal evolution. This paper proposes the use of an alternative event representation based on nonlinear time normalization prior to the extraction of mid-term statistics. The short-term features are transformed into a new fixed-length representation that considers uniform distance subsampling over a defined feature space in contrast to the classical short-term temporal framing. The results show that the use of distance-based texture windows provides an improved statistical description of the event robust to errors in the event segmentation stage under noisy conditions.

International audience; Since 2017, the goal of the two-million song WASABI database has been to build a knowledge graph linking collected metadata (artists,discography, producers, dates, etc.) with metadata generated by the analysis of both the songs’ lyrics (topics, places, emotions, structure, etc.) and audio signal (chords, sound, etc.). It relies on natural language processing and machine learning methods for extraction, and semantic Web frameworks for representation and integration. It describes more than 2 millions commercial songs, 200K albums and 77K artists. It can be exploited by music search engines, music professionals (e.g. journalists, radio presenters, music teachers) or scientists willing to analyze popular music published since 1950. It is available under an open license, inmultiple formats and with online and open source services including aninteractive navigator, a REST API and a SPARQL endpoint.

Audio signals generated by the human body (e.g., sighs, breathing, heart, digestion, vibration sounds) have routinely been used by clinicians as indicators to diagnose disease or assess disease progression. Until recently, such signals were usually collected through manual auscultation at scheduled visits. Research has now started to use digital technology to gather bodily sounds (e.g., from digital stethoscopes) for cardiovascular or respiratory examination, which could then be used for automatic analysis. Some initial work shows promise in detecting diagnostic signals of COVID-19 from voice and coughs. In this paper we describe our data analysis over a large-scale crowdsourced dataset of respiratory sounds collected to aid diagnosis of COVID-19. We use coughs and breathing to understand how discernible COVID-19 sounds are from those in asthma or healthy controls. Our results show that even a simple binary machine learning classifier is able to classify correctly healthy and COVID-19 sounds. We also show how we distinguish a user who tested positive for COVID-19 and has a cough from a healthy user with a cough, and users who tested positive for COVID-19 and have a cough from users with asthma and a cough. Our models achieve an AUC of above 80% across all tasks. These results are preliminary and only scratch the surface of the potential of this type of data and audio-based machine learning. This work opens the door to further investigation of how automatically analysed respiratory patterns could be used as pre-screening signals to aid COVID-19 diagnosis., Comment: 9 pages, 6 figures, 2 tables, Accepted for publication at KDD'20 (Health Day)

Estimating the pitch, or fundamental frequency, of a monophonic audio signal is a fundamental task in computational audio analysis with many downstream applications such as automatic transcription. The current general state of the art method for pitch detection is CRePE: a Convolutional Representation for Pitch Estimation. CRePE is a deep convolutional neural network designed to estimate the fundamental frequency of an audio signal directly from the waveform. However, CRePE, and other general pitch detection methods, do not perform well on steelpan audio. This is likely due to the steelpan's complex spectral characteristics that differentiate it timbrally from other sound sources. We combine a deep convolutional neural network architecture based on CRePE with a training dataset of steelpan audio from several distinct sounding tenor steelpans to achieve improved tenor steelpan pitch detection directly from the audio signal. We assess our model's ability to generalize by evaluating it with a test dataset that includes audio samples from steelpans that have no samples as part of the training set and compare these results to CRePE's performance on the same test dataset.

The estimation of fundamental frequency, or pitch, is a fundamental task in computational audio analysis with a variety of applications. Steelpan audio has proven difficult for general pitch detection methods CRePE and pYin. CRePE is a method that uses a deep convolutional neural network to perform pitch estimation directly from the audio signal while pYIN is a digital signal processing-based approach. Audio feature extraction is the process of using digital signal processing techniques to extract low level audio information from signals. Combining audio feature extraction with logistic regression is currently the best performing steelpan pitch estimation method, but the efficacy of using deep neural networks in lieu of traditional machine learning algorithms has yet to be determined. This paper compares the performance and computational requirements of a deep neural network-based architecture against logistic regression as well as the established pYIN and CRePE pitch detection methods to determine which method is the most accurate and efficient. All of these methods are evaluated on a test dataset containing one-hit audio samples from several distinct sounding steelpans. Generalization to other steelpans is assessed by including samples in the test dataset from steelpans for which no samples are in the training dataset.

Objective.When recording a subject in an at-home environment for sleep evaluation or for other breathing disorder diagnoses using non-contact microphones, the breathing recordings (audio signals) can be distorted by sounds such as TV, outside noise, or air-conditioners. If two people are sleeping together, both may produce breathing/snoring sounds that need to be separated. In this study, we present signal processing and source separation algorithms for the enhancement of individual breathing/snoring audio signals in a simulated environment.Approach.We developed a computer simulation of mixed signals derived from genuine nocturnal recordings of 110 subjects. Two main source separation approaches were tested: (1) changing the basis vectors for the mixtures in the time domain (principal and independent component analysis, PCA/ICA) and (2) converting the mixtures to their time-frequency representations (degenerate un-mixing estimation technique, DUET). In addition to these source separation techniques, a beamforming approach was tested.Main results.The separation results with a reverberation time of 0.15 s and zero SNR between signals showed good performance (mean source to interference ratio (SIR): DUET = 12.831 dB, ICA = 3.388 dB, PCA = 4.452 dB), and for beamforming (SIR = -0.304 dB). To evaluate our source separation results, we propose two new measures: an evaluation measure based on a spectral similarity score (mel-SID) between the target source and its estimation (after separation) and a breathing energy ratio measure (BER). The results with the new proposed measures yielded comparable conclusions (mel-SID: DUET = 1.320, ICA = 2.732, PCA = 1.927, and beamforming = 2.590, BER: DUET = 10.241 dB, ICA = 0.270 dB, PCA = -2.847 dB, and beamforming = -1.151 dB), but better differentiated the differences between the performance of the algorithms. The DUET is superior on all measures. Its main advantage is that it only uses two microphones for separation.Significance. The separated audio signal can thus contribute to a more informed diagnosis of sleep-related and non-sleep-related diseases. The Institutional Review Committee of Soroka University Medical Center approved this study protocol (protocol number 10141) and all methods were performed in accordance with the relevant guidelines and regulations.

Recent work at the Sussex Humanities Lab, a digital humanities research program at the University of Sussex, has sought to address an identified gap in the provision and use of audio feature analysis for spoken word collections. Traditionally, oral history methodologies and practices have placed emphasis on working with transcribed textual surrogates, rather than the digital audio files created during the interview process. This provides a pragmatic access to the basic semantic content, but obviates access to other potentially meaningful aural information; our work addresses the potential for methods to explore this extra-semantic information, by working with the audio directly. Audio analysis tools, such as those developed within the established field of Music Information Retrieval (MIR), provide this opportunity. This paper describes the application of audio analysis techniques and methods to spoken word collections. We demonstrate an approach using freely available audio and data analysis tools, which have been explored and evaluated in two workshops. We hope to inspire new forms of content analysis which complement semantic analysis with investigation into the more nuanced properties carried in audio signals.

This work treats the estimation of chroma features for harmonic audio signals using a sparse reconstruction framework. Chroma has been used for decades as a key tool in audio analysis, and is typically formed using a periodogram-based approach that maps the fundamental frequency of a musical tone to its corresponding chroma. Such an approach often leads to problems with tone ambiguity. We address this ambiguity via sparse modeling, allowing us to appropriately penalize ambiguous estimates while taking the harmonic structure of tonal audio into account. Furthermore, we also allow for signals to have time-varying envelopes. Using a spline-based amplitude modulation of the chroma dictionary, the presented estimator is able to model longer frames than what is conventional for audio, as well as to model highly time-localized signals, and signals containing sudden bursts, such as trumpet or trombone signals. Thus, we may retain more signal information as compared to alternative methods. The performances of the proposed methods are evaluated by analyzing the average estimation errors for synthetic signals, as compared to the Cramer-Rao lower bound, and by visual inspection for estimates of real instrument signals. The results show strong visual clarity, as compared to other commonly used methods. HighlightsTwo chroma estimators are proposed, exploiting the harmonic structure of music.A sparse modeling framework is used, not requiring explicit model order knowledge.One estimator assumes stationarity, promoting chroma with spectrally smooth partials.One estimator allows for amplitude modulation by using a B-spline representation.A Cramer-Rao lower bound is derived for the chroma-specific signal model.

The reporting on nocturnal sounds like cough and snore is not only relevant to follow the progress of respiratory diseases of patients but also to assess the quality of sleep of subjects. In this study, we discuss an audio analysis approach to count individual cough events and the duration of snore sounds in presence of air-conditioner noise through recordings of a smartphone and computationally efficient classifiers. A new audio data set of cough and snore sounds was acquired from 26 subjects. Energy threshold-based segmentation was applied to identify cough or snore events in the original low noise dataset. A k-nearest neighbor classifier was trained to merge cough phases belonging to the same cough event, to derive the proper ground-truth labeling. The original audio signal was augmented by the superposition of air-conditioner noise, with a signal-to-noise ratio of -40dB to 40dB, to enrich the training set of the binary classifier. Nine out of 40 mel-frequency cepstral coefficients in combination with the logarithm of energy from an entire cough or snore event were computed. Various classifiers, such as k-nearest neighbor (k-NN), rule-based classifier, decision tree, random forest, naive Bayes, and support vector machine were benchmarked against each other. The k-NN classifier with k=1 resulted in the highest F_ 1 scores of.85 and.88 in the binary classification task using generalized and personalized models, respectively, considering noise augmented samples. These results underline the potential of smartphones to objectively report on patient symptoms through audio recordings at night.

A novel improvement to an existing wavelet representation is presented within the context of analysis and synthesis of harmonic audio signals. The approach replaces the discrete wavelet transform stage in the harmonic-band wavelet transform with the dual-tree complex wavelet transform. The harmonic-band wavelet transform lacks explicit phase information, is subject to considerable transform domain coefficient aliasing and its filters exhibit poor frequency selectivity and high sidelobe levels. Integration of the dual-tree complex wavelet transform mitigates all of these disadvantages and significantly improves the accuracy of signal synthesis where signals are synthesised through autoregressive analysis and linear prediction of transform domain coefficients.

In the era of third generation surveillance systems, it becomes more and more useful to have available a solution able to automatically detect abnormal events. The interest for audio analysis is thus growing in the last years, due to the large amount of situations where a microphone and an audio surveillance system can be profitably used by the human operator in charge of control. In this paper, we propose a method for automatically analyzing the audio stream for surveillance purposes: it is able to detect the presence of abnormal events such as screams, gun shots and broken glasses. Instead than processing directly raw data (the audio signal), the stream is represented by means of an image, namely the spectrogram, a time-frequency representation of the audio stream. In this way, we formulate the problem of audio analysis as a problem of image classification. Thus, we propose to use a Convolutional Neural Network with the following two main properties: inspired by VGG network, we employed very small kernels in convolutional layers; furthermore, we adopted a pyramidal structure in fully connected layers. These choices allow to have good generalization capabilities of the network even in presence of a not so wide dataset. The performance, computed over a standard dataset already used for benchmarking purposes in the field of audio surveillance, confirms the effectiveness of the proposed approach.

Acknowledging the advantages as well as the dangers of the internet content on kids education and entertainment, YouTube Kids was created. Based on regulations for child-friendly programs, several violations are identified and restricted from viewable content. When a child surfs the Internet, the same regulations could be automatically detected and filtered. However, current YouTube Kids content filtering relies on meta-data attributes, where inappropriate content could pass the filtering mechanism. This research, propose an advanced real-time content filtering approach using automated video and audio analysis as an extra layer for kids safety. The proposed method utilizes the thin-slicing theory, where several one second slices are selected randomly from the clip and extracted. The use of a one-second slice will assure a temporal analysis of the clip content, and ensures a real-time content analysis. For each slice, audio is automatically transcribed using automatic speech recognition techniques to be further analysed for its linguistic content. Furthermore, the audio signal is analysed to detect event and scenes (e.g. explosion). The image frames extracted from the slices are also inspected for its content to avoid inappropriate scenes, such as violence. Upon the success of this approach on YouTube Kids application, investigation of its generalizability to other video applications, and other languages could be performed.

In this paper, we discuss a method for a music performance detail analysis using multiresolution analysis allowing simultaneous estimation of pitch, precise onset, duration and intensity from polyphonic audio. The motivation is to obtain information that is detailed enough to develop a performance model of a human player. Characteristics of human performance can be observed as local and global tempo changes, sound intensity (volume or velocity in a MIDI), and articulations like slur and staccato. Estimation and extraction of such features from a musical audio signal in detail is useful for music information retrieval systems, automatic transcription systems, as well as automatic performance systems to train the relationship between music features and player performance. Our proposed system is based on non-negative matrix factorization (NMF) using hierarchical Bayesian inference, which is modeling harmonic and nonharmonic structures, note durations, intensities, and onset information stochastically. The estimation process comprises two steps. In the first step, variational Bayesian inference and a Gaussian mixture model is used to roughly estimate pitch onset, intensity and duration. These values are used as a prior for the second more detailed step, in which time resolution is doubled and the estimation is repeated to refine the results. The evaluation results show that the our proposed multiresolution Bayesian model can estimate more precise onset times and durations than our non-multiresolution Bayesian model.

Like the concept of free-viewpoint TV (FTV), the audio data should be rendered according to video data. However, on condition that minimum numbers of microphone are used, it is difficult to acquire accurate audio signal for rendering audio data to the image with the choice of view point. Especially, degradation of high frequency components (HFC) happens due to the characteristic of polar pattern for microphone. The degradation of HFC causes imperfection of signal restoration and leads to the degradation of clarity for hearing. In this paper, a compensation method for the degradation of HFC audio signal is proposed for producing an immersive audio effect at realistic media. Our experimental results show that low frequency components (LFC) of audio signal had a little directional degradation in spite of effect of the polar patterns of microphone and the compensation of HFC can be realized with adapting the attenuation inclination of LFC. This research is expected to be helpful for producing an immersive audio effect for a realistic media.

Non-negative matrix factorization (NMF) is a traditionalsignal processing technique that allows approximating a measured spectrum as a weighted sum of known spectra. It may be applied to automatic transcription of piano music by assuming that each note is related to a known spectral template. In this model, active notes are related to peaks that can be identified by thresholding. We show that the optimal threshold is highly dependent on the timbre of the particular instrument used to play the analysed audio file. This can cause difficulties to the transcription. We propose an unsupervised technique that allows finding a threshold based on known properties of the audio signal. We show that the proposed technique’s performance compares favourably with manual threshold optimization. Moreover, we provide instructions and source codes that allow reproducing all described experiments.

The bandwidth limitation of wideband audio systems degrades the subjective quality and naturalness of audio signals. In this paper, a new method for blind bandwidth extension of wideband audio signals is proposed based on ensemble echo state network with temporal evolution. The high-frequency components in the band of $7 \sim 14\ \text{kHz}$ are artificially restored only from the information in the wideband audio. For each region in the wideband feature space, a specific echo state network with recurrent structure is explored to dynamically model the local mapping relationship between wideband audio features and high-frequency spectral envelope. The transition process among regions is modeled by a hidden Markov model, and a network ensemble technique based on temporal evolution is used to fuse multiple echo state networks such that the high-frequency spectral envelope is estimated. Combining the high-frequency fine spectrum extended by spectral translation, the proposed method can effectively extend the wideband audio to super wideband. In addition, the proposed extension method is applied to the ITU-T G.729.1 wideband audio codec and is further evaluated in comparison with the ITU-T G.729.1 Annex E super-wideband audio codec and the hidden Markov model-based reference bandwidth extension method. Objective quality evaluation results indicate that the proposed method is preferred over the hidden Markov model-based reference bandwidth extension method in terms of log spectral distortion, cosh measure, and differential log spectral distortion. Further, the proposed method improves the auditory quality of the wideband audio and also gains a good performance in the subjective listening tests.

Snoring is one the earliest symptoms of OSAS and is considered a coarse indicator of muscular tone deficiency that may compromise the regular breathing cycle. The present work intends to systematize the snore audio analysis in a cross-sectional study, with convenience sampling, of 67 individuals that undertook multi-parametric PSG analysis, during the diagnostics and OSAS severity classification process. A complete recording audio session was performed for each of the subjects while undergoing a PSG at the clinical facilities. Audio records were offline processed, in order to synchronize with the PSG data, and to determine the individual events (snores) features such as timing and Shannon entropy. This latter is taken as a stochastic measurement of complexity of the snore events and cross correlated with the clinical 5-class classification (Control, Snore, Mild, Moderate, or Severe) performed by the clinical team. For each patient, the 75–25 percentile difference, for the set of entropy values, has been calculated and the determined values were clustered according to the patients’ medical class. The statistical distribution of each class returns parameters evolving with OSAS severity in a strictly monotonic behaviour. Those parameters are p50c − p25c, and p50c and p25c after the introduction of a weighting factor. These are, therefore, the best features to be used on an event driven analysis of time-series snores that aims at class discrimination.

Passive microphones and instrument pickups output very small voltages, requiring a preamplifier to feed devices having line-level inputs. Where most consumer audio equipment uses a nominal level of −10 dBV, professional audio gear operates at a level of +4 dBm. Besides using a higher signal level to overcome noise and hum, most pro audio gear can also drive low-impedance inputs and longer cable lengths without increasing distortion and cross-talk or losing high frequencies. High-impedance instrument pickups work best when driving high-impedance inputs to maintain a flat frequency response, though most audio gear has a low output impedance and high input impedance to allow feeding several inputs at once.

The train safety guarantees the passenger travel. It is important to detect the train faults timely. This study proposes the audio analysis technology to detect the fault of train. Use the audio equipment to obtain the train audio, so as to analyze and deal with the train audio, obtain the train audio characteristic value, and finally use the eigenvalue to analyze the train audio fault analysis, effectively find out the audio fault. The wavelet packet algorithm and ART-2 Neural Network algorithm are applicated in the train fault detection. First, the wavelet packet analysis is used in the train audio analysis feature extraction, which is commonly used in modern signal analysis process. Then, the ART-2 Neural Network is used to identify the different states to judge the train fault effectively through simulation. Through the experiment found that the use of algorithms can accurately find out the audio failure. The wavelet packet analysis algorithm is not only good for low frequency signal analysis, but also can be used for high frequency signal analysis, can fully understand the characteristics of audio signals. Feature extraction refers to the state signal and equipment failure related to the information extracted.

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.

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.

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.

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.

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.

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

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.

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.

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.

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.

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.

Enhancing speech from audio signals recorded using several microphones is of interest to many audio applications such as human-computer interfaces and teleconference systems. With an increasing availability of low-cost micro-electro-mechanical systems (MEMS) and powerful processing units, embedded systems are capable of recording and processing several audio signals in realtime. In this paper, an overview of the entire signal processing chain from audio signal acquisition with an array of MEMS microphones to the signal enhancement using directional filtering is provided. The presented results indicate that good noise and interference suppression can be achieved in realtime using an embedded system equipped with low-cost microphones.

Research on robot perception mostly focuses on visual information analytics. Audio-based perception is mostly based on speech-related information. However, non-verbal information of the audio channel can be equally important in the perception procedure, or at least play a complementary role. This paper presents a framework for audio signal analysis that utilizes the ROS architectural principles. Details on the design and implementation issues of this workflow are described, while classification results are also presented in the context of two use-cases motivated by the task of medical monitoring. The proposed audio analysis framework is provided as an open-source library at github (https://github.com/tyiannak/AUROS).

Position information of sound source provides important cues for many audio analysis tasks. In this paper, we present a simple yet effective simultaneous audio source location and microphone placement approach to obtain the position information of stationary sound source. Motivation by the fact that audio source location and microphone placement can help each other, we consider these tasks as a joint inference framework so that more contextual information can be exploited. By fusing geometric properties of the sliding microphone-pair system with an error theory analysis, our location approach can achieve higher accuracy than conventional methods theoretically. Moreover, experimental results on our built real sound source location system are presented to demonstrate the effectiveness of the proposed approach.

This study proposes a CMOS MEMS audio transducer implemented by combining a silicon condenser microphone with analog front-end audio codec circuits. The proposed CMOS MEMS audio transducer is attractive because the sensor and all the circuits are robustly and compactly integrated. The overall size of the proposed device is much smaller than traditional electrets-condenser microphones (ECMs). Another innovation of the proposed CMOS MEMS audio transducer is that it can operate without any charge pump circuits, which overcomes the problem of requiring a high bias voltage. Measurement results confirm the correct functions and performance of the proposed CMOS MEMS audio transducer. The area of the proposed CMOS MEMS audio transducer is 1352×1410 μm2 and the FOM of the proposed sigma-delta modulator is 148 dB. The proposed CMOS MEMS audio transducer is suitable for audio devices, such as audio codecs.

Nowadays, audio channels in musical concerts (as well as in cabins as in live concerts) start from analogical audio signals generated at microphones, continue with signal transmission to a central audio mixer through wire connections (a wire for each microphone) and end at its digital processing and posterior reproduction through audio system speakers. Algorithm proposed by the authors suggests the signal digitalization directly at microphones and the introduction of virtual audio mixers, which simplifies audio channels management, and reproduces equalization and volume control functions from physical ones, adding control mechanisms over output channels. Noise and attenuation levels are measured and compared with traditional systems, to demonstrate the advantages of using the proposed algorithm.

Audio information plays a rather important role in the increasing digital content that is available today, resulting in a need for methodologies that automatically analyze such content: audio event recognition for home automations and surveillance systems, speech recognition, music information retrieval, multimodal analysis (e.g. audio-visual analysis of online videos for content based recommendation), etc. This paper presents pyAudioAnalysis, an open-source Python library that provides a wide range of audio analysis procedures including: feature extraction, classification of audio signals, supervised and unsupervised segmentation and content visualization. pyAudioAnalysis is licensed under the Apache License and is available at GitHub (https://github.com/tyiannak/pyAudioAnalysis/). Here we present the theoretical background behind the wide range of the implemented methodologies, along with evaluation metrics for some of the methods. pyAudioAnalysis has been already used in several audio analysis research applications: smart-home functionalities through audio event detection, speech emotion recognition, depression classification based on audio- visual features, music segmentation, multimodal content-based movie recommendation and health applications (e.g. monitoring eating habits). The feedback provided from all these particular audio applications has led to practical enhancement of the library.

In this paper, the subjective audio quality of various digital radio systems is evaluated. In order to estimate the true audio quality of a commercial digital radio service, test audio signals were acquired directly from the digital radio equipment in the field. Twenty-one subjects participated in the test after pre-screening. The evaluation process consisted of two phases. In the first phase, the audio quality of each system was evaluated as a function of the bit rates, and the relationship between the audio quality and the channel capacity of each system was obtained. In order to confirm the evaluation consistency, in the second phase, the audio quality as a function of the systems was evaluated. Assuming that the digital radio equipment tested in this paper is used for service, these evaluation results provide the true audio quality of commercial digital radio services for various types of systems and bit rates, and can be used as a reference to determine the optimal channel capacity of digital radio service for a given target audio quality.