Audio Signal Enhancement Research Articles

Drone audition: Audio signal enhancement from drone embedded microphones using multichannel Wiener filtering and Gaussian-mixture based post-filtering

In this paper, we consider the problem of recovering desired sound source signals from on-board microphone recordings on a noisy drone. Enhancement of source signal degraded by drone noise is considered to be a difficult task due to the strong noise generated from its motors and propellers causing an extremely low signal-to-drone noise ratio (SD‾NR). We propose a solution (i) by combining the widely known multichannel Wiener filter (MWF) to remove drone noise from microphone recordings, and (ii) further reduction of residual noise using a Gaussian mixture model (GMM) based dual-stage parametric Wiener filter (WF). The method exploits known statistics of motor current-specific drone noise. This combination of techniques to the specific context of signal enhancement for drone audition is applicable to irregular microphone arrays embedded on a drone enabling realistic integration to most drones. We demonstrate the validity of the proposed framework with extensive real data through (i) experimental recordings from two different drone acoustics datasets and (ii) outdoor measurements from a hovering drone for a bioacoustic application. The results confirm improved performance in terms of SD‾NR, speech quality (PESQ), and intelligibility (STOI) at very low SD‾NR (up to −30 dB) and show a strong potential for signal enhancement applications using noisy drones.

Drone audition: improved Gaussian mixture model Wiener filtering approach for audio signal enhancement

Audio signal enhancement is an integral function of drone audition systems which emerges intelligent audio applications for military and civil environments. Signal enhancement using a drone is challenging due to its emission of significant noise from drone motors and propellers resulting in an extremely low signal-to-drone noise ratio level. A method for signal enhancement from an on-board microphone array on a drone for static flight conditions in adverse noisy environments is proposed. In this paper, we present an improved Gaussian mixture model Wiener filter approach for a noisy drone platform in the presence of interfering noise sources such as wind, and traffic. The key to this method is to exploit the spatial properties of the noise sources by using a set of Gaussian components to derive an accurate estimate of the power spectral densities of both residual drone noise and interfering noise sources to obtain the enhanced target sound source signal. We demonstrate the method's general applicability for both speech, and bird calls using an extensive experimental study, including an experimental recording from a drone acoustics dataset using measured impulse responses, and an outdoor measurement from a hovering drone for a bioacoustic application, respectively.

Enhancing Speech Signal Quality through Noise Reduction for Improved Communication

Abstract: Speech is a fundamental and reliable mode of human communication, conveying not only linguistic content but also essential cues about the speaker, including language, emotion, gender, and identity. However, in contemporary telephone and audio-based communication systems, speech signals are highly susceptible to the deleterious effects of ambient and Gaussian noise. To detach this noise from the signal, many Digital Audio Filters can be employed, including the Audio Weighting Filter, low-pass and High-pass filter, Band Pass Filter, and Band Stop Filter. This paper implements and compares various digital filters for audio signal enhancement using MATLAB Simulink and compares the outcome to identify the best filter for this specific purpose.

Enhancing Audio Signal Quality and Learning Experience with Integrated Covariance Weiner Filtering in College Music Education

In recent years, computer music technology has become increasingly prevalent in college music education, offering new possibilities for creative expression and pedagogical approaches. This paper concentrated on the music education in the colleges with the application of integrated time and frequency filtering (ITFF) with Kalman integrated covariance Weiner filtering in college music education. The ITFF technique combines time and frequency domain analysis to enhance the quality and clarity of audio signals. By integrating the Kalman integrated covariance Weiner filtering, the ITFF method provides robust noise reduction and improved signal representation. This integrated approach enables music educators to effectively analyze and manipulate audio signals in real-time, fostering a more immersive and engaging learning environment for students. The findings of this study highlight the benefits and potential applications of ITFF with Kalman-integrated covariance Weiner filtering in college music education, including audio signal enhancement, sound synthesis, and interactive performance systems. The integration of computer music technology with advanced filtering techniques presents new opportunities for exploring sound, composition, and music production within an educational context.

Fused Lasso Algorithm Based on Novel Non-Convex Regularization in Sparse Domain for Audio Signal Enhancement

In this work, we present the fused lasso algorithm in the wavelet domain for audio signal enhancement. The fused lasso algorithm gives more efficiency than other methods because this algorithm comprises two parts. The first part is called as the total variation method (TVM), and the second part is known as the penalized least squares regression (PLSR). The prominent point of the TVM is based on decreasing the pseudo-Gibbs phenomena. On the other hand, the PLSR with the convex condition, also called as the convex PLSR, gives the advantage in reducing noise. A lot of works study and develop the TVM; therefore, we focus on developing the convex PLSR in this work. In fact, the bias which is the gap between the estimated and noisy signals at the large magnitude of the noisy signal affects the performance of the convex PLSR. If this bias is small, also known as the small bias, then the convex PLSR gives better efficiency than other forms. Therefore, we present the novel non-convex regularization which can build the convex PLSR in the closed-form solution and the small bias. Here, the convex PLSR of the proposed regularization is presented not only in the closed-form solution and the small bias but also in the relationship to the group of wavelet coefficients, also called as the multivariate case. In the signal enhancement problem, experimental results show that the fused lasso algorithm and the convex PLSR based on the proposed regularization outperform state-of-the-art techniques in both the error of the [Formula: see text] norm (L2E) and visual quality.

Audio Signal Extraction and Enhancement Based on CNN From Laser Speckles

A micro vibration signal extraction method based on deep neural network is proposed. Rough surface of vibrating object modulates the illuminating laser wave front and generates speckle pattern, which is recorded by a linear array CMOS and preprocessed and input into a 16-layer convolution neural network (CNN) trained with specially prepared data. The optical experimental setup is analyzed to fulfil the temporal and spatial Shannon sampling theorem. The output audio signals are evaluated with standard algorithms and show enhanced segmental SNR and intelligibility. The effects of different input audio types and quality of raw audio signals are investigated, and the results show that the neural network is robust to the input. The CNN structure is optimized and the results show the performance decrease with the reduction of convolution layers. The performances of three popular deep neural networks are compared and the performance of CNN is better.

Spatial Audio Signal Enhancement by a Two-Stage Source—System Estimation With Frequency Smoothing for Improved Perception

Spatial Audio Signal Enhancement by a Two-Stage Source—System Estimation With Frequency Smoothing for Improved Perception

Multilayered convolutional neural network-based auto-CODEC for audio signal denoising using mel-frequency cepstral coefficients

The denoising of audio signal and quality enhancement has a substantial contribution in speaker identification, audio transmission, hearing aids, microphones, mobile phones, etc., Hence, an efficient denoising method is required to enhance the audio signal quality securely. A robust multilayered convolutional neural network (MLCNN)-based auto-CODEC for audio signal denoising which is utilizing the mel-frequency cepstral coefficients (MFCCs) has been proposed in this research. The MLCNN takes the input as MFCC with different frames from the noise-contaminated audio signal for training and testing. The proposed MLCNN model has been trained and tested as 80:20 ratios for the available MIT database. After the training, the proposed method has been validated. From the validation, it has been found that the proposed MLCNN model provides an accuracy of 93.25%. The performance of MLCNN has been evaluated and compared with the reported methods using short-time objective intelligibility (STOI), perceptual evaluation of speech quality (PESQ) and cosine similarities. From the performance comparisons, it has been found that the proposed MLCNN model outperforms other models. From the cosine similarity, it has been proved that MLCNN provides high security level which can be used for many secure applications.

Audio signal quality enhancement using multi-layered convolutional neural network based auto encoder–decoder

In this research article, a multi-layered convolutional neural network (MLCNN) based auto-CODEC for audio signal enhancement which is utilizing the Mel-frequency cepstral coefficients (MFCC) has been proposed. The proposed MLCNN takes the input as MFCC with different frames from the noise contaminated audio signal for training and testing. The proposed MLCNN models has been trained and tested as 80:20 and 70:30 ratios from the available database. The proposed method has been verified and validated MNIST database. From the validation it has been found that the proposed MLCNN model provides an accuracy of 93.25%. The performance of MLCNN has been evaluated using short-time objective intelligibility, perceptual evaluation of speech quality and Cosine similarities. The proposed MLCNN model has been compared with the reported models. Form the comparisons; it has been observed that the proposed MLCNN model outperforms other models. From the cosine similarity, it has been proved that MLCNN provides high security level which can be used for many secure applications.

Audio Signal Detection and Enhancement Based on Linear CMOS Array and Multi-Channel Data Fusion

An audio signal detection system based on laser speckle and multi-channel data fusion is presented. A linear CMOS array is used as the detector, which owns a fast line rate and suitable sensing size. The signals from the pixels are selected and fused to enhance the reconstructed signal. The reconstructed audio signals are evaluated with a segmental SNR (SegSNR) algorithm. The experimental results of three categories of audio sources (single voice audio, conversation and music) show that data fusion can improve the SegSNR scores. Especially, direct phase-error based filtering (pbf) fusion gives a nearly 3.0 dB increase and obtains another 1.0 dB increase with the combination of single channel process. The experimental results show that the fusion algorithms are not sensitive to audio types and the performance of multi-channel data fusion is not weakened with the increase of measuring distance. This feature has potential applications in remote sensing. The intelligibility of the fused audio signals is evaluated with normalized subband envelope correlation (NSEC) algorithm and the evaluation results shows that fusion can also enhance the intelligibility of the recovered signal.

Robust and adaptive diffusion-based classification in distributed networks

Distributed adaptive signal processing and communication networking are rapidly advancing research areas which enable new and powerful signal processing tasks, e.g., distributed speech enhancement in adverse environments. An emerging new paradigm is that of multiple devices cooperating in multiple tasks (MDMT). This is different from the classical wireless sensor network (WSN) setup, in which multiple devices perform one single joint task. A crucial first step in order to achieve a benefit, e.g., a better node-specific audio signal enhancement, is the common unique labeling of all relevant sources that are observed by the network. This challenging research question can be addressed by designing adaptive data clustering and classification rules based on a set of noisy unlabeled sensor observations. In this paper, two robust and adaptive distributed hybrid classification algorithms are introduced. They consist of a local clustering phase that uses a small part of the data with a subsequent, fully distributed on-line classification phase. The classification is performed by means of distance-based similarity measures. In order to deal with the presence of outliers, the distances are estimated robustly. An extensive simulation-based performance analysis is provided for the proposed algorithms. The distributed hybrid classification approaches are compared to a benchmark algorithm where the error rates are evaluated in dependence of different WSN parameters. Communication cost and computation time are compared for all algorithms under test. Since both proposed approaches use robust estimators, they are, to a certain degree, insensitive to outliers. Furthermore, they are designed in a way that they are applicable to on-line classification problems.

Development of the Audio Enhancement Method by Using the Reflected Signals in the Reverberant Environment

This paper presents a new audio signal enhancement method based on reflection signal detection in the reverberant environment. This technique enhances the audio signal from the target sound source in time domain. The advantages of this technique are enhancing the target sound source by a simple algorithm and reducing the background noise effectively. The effects of distances between the speaker and microphone and the coefficient of correlation are discussed in this paper. The coefficient of correlation is rising from 0.17 to 0.63 as the distance between the speaker and microphone is varying from 30 to 90 cm. Also, some antinoise experiments are carried out in this study and the results show that the audio enhancement algorithm provides a good antinoise performance in different background noise levels.

Audio signal enhancement and amplification system

An audio system includes amplifying with distortion via a first amplifier electrical audio signals from a sound source, such as an electric guitar, for example, to obtain a desired tonal quality in the sound produced from a first loudspeaker driver by the amplified electrical audio signals, simultaneous with applying electrical signals from a piezo film transducer attached to the cone of the first loudspeaker to a second amplifier having a flat response over a desired frequency range, and adjustable low and high frequency rolloff, for driving a second loudspeaker to produce desired perceived tonal quality at relatively low sound pressure levels, with the volume of the sound from the first and second loudspeakers being adjusted to match the acoustics of a room in which the audio system is operating.

Efficient Alternatives to the Ephraim and Malah Suppression Rule for Audio Signal Enhancement

Audio signal enhancement often involves the application of a time-varying filter, or suppression rule, to the frequency-domain transform of a corrupted signal. Here we address suppression rules derived under a Gaussian model and interpret them as spectral estimators in a Bayesian statistical framework. With regard to the optimal spectral amplitude estimator of Ephraim and Malah, we show that under the same modelling assumptions, alternative methods of Bayesian estimation lead to much simpler suppression rules exhibiting similarly effective behaviour. We derive three of such rules and demonstrate that, in addition to permitting a more straightforward implementation, they yield a more intuitive interpretation of the Ephraim and Malah solution.

Monte Carlo smoothing with application to audio signal enhancement

We describe methods for applying Monte Carlo filtering and smoothing for estimation of unobserved states in a nonlinear state-space model. By exploiting the statistical structure of the model, we develop a Rao-Blackwellized particle smoother. Due to the lengthy nature of real signals, we suggest processing the data in blocks, and a block-based smoother algorithm is developed for this purpose. All the algorithms suggested are tested with real speech and audio data, and the results are shown and compared with those generated using the generic particle smoother and the extended Kalman filter (EKF). It is found that the proposed Rao-Blackwellized particle smoother improves on the standard particle smoother and the extended Kalman smoother. In addition, the proposed block-based smoother algorithm enhances the efficiency of the proposed Rao-Blackwellized smoother by significantly reducing the storage capacity required for the particle information.

A Bayesian framework for perceptually motivated audio signal enhancement

Spurred by the success of perceptual models in audio coding applications, researchers have begun to address audio signal enhancement in a similar manner. Here a statistical model-based approach is presented that uses cost functions based on auditory perception. As noise reduction inevitably occurs at the expense of signal resolution, why not take advantage of human perception in order to optimize this trade-off? By mathematically incorporating the notion of perceived signal quality, Bayesian risk theory does just that. The Bayesian paradigm is shown to provide an ideal framework within which to formalize such an approach, as it is rigorous, powerful, and generalizable. At the same time it allows the incorporation not only of psychoacoustic optimality criteria, but also of additional nonperceptual prior information such as that concerning audio signal behavior in time and frequency. Importantly, it also permits sequential estimation for real-time noise reduction. Audio examples and the corresponding noise reduction software may be found at http://www-sigproc.eng.cam.ac.uk/∼pjw47. [Material by the first author is based upon work supported by a U.S. National Science Foundation graduate research fellowship.]

Perceptually Motivated Approaches to Music Restoration

Spurred by the success of perceptual models in audio coding applications, researchers have recently begun to address audio signal enhancement in a similar manner. Here we consider the case of musical recordings degraded by additive broadband noise such as tape hiss, in which the prevention of signal distortion is tantamount to noise removal. We review perceptually motivated approaches to music restoration and describe a statistical model based framework we have recently proposed. By integrating psychoacoustics into the restoration process through the use of perceptual optimality criteria, our method aims to take advantage of human auditory perception to yield improvements in both noise reduction and perceived signal fidelity. Audio examples and related software may be found at http://www.sigproc.eng. cam.ac.uk/~pjw47.

Neuro-rough control of masking thresholds for audio signal enhancement

The paper addresses the problem of neuro-rough hybridisation applied to digital processing of audio signals. Moreover, the application of some selected soft computing techniques to non-stationary noise reduction is described. Some attention is also put to a discussion of the intelligent decision algorithms performance. The noise reduction algorithm is based on the new perceptual approach exploiting some properties of the human auditory system. Furthermore, the paper introduces the engineered perceptual filter driven by an intelligent controller employing rules generated with the use of a rough set-based algorithm supported by a neural network. The goal of the intelligent controller is to estimate the current statistics of corrupting noise on the basis of the analysis of signals received from telecommunication channel. Thereafter, the noise estimate enables determining the masking threshold levels which allow making the noise inaudible in the audio signals. Since the implemented decision algorithm requires quantised data, thus the Kohonen's self-organising maps (SOM) extended by various distance metrics were used as data quantisers. Some results of the experiments in the domain of non-stationary noise reduction in speech are discussed in the paper.

Overview of blind signal separation, part II: Structures and applications

The focus of this talk is a class of blind signal separation procedures, blind separation of convolutive mixing of signals. The emphasis is on acoustic signals and methods applicable thereof, and their capabilities and limitations. At least two possible taxonomies of separation methods are possible. These are based on how to parametrize the separating structure, and on the criteria used for separation. The former will be the emphasis of the presentation. Different criteria to solve the problem are only briefly touched upon. Possible application areas are enumerated, especially in acoustics. Two exemplary areas are audio signal enhancement in the presence of disturbing noise, and machine vibration analysis. Some issues on why it is not straightforward to move blind separation techniques into real world applications are elaborated. Limitations in the audio setup are discussed that make unconstrained BSS an extremely hard (if indeed solvable) problem. Some further questions are posed and directions for further research are presented.

Objective estimation of perceived speech quality .II. Evaluation of the measuring normalizing block technique

For pt.I see ibid., vol.7, no.4, p.371-82. Part I of this paper describes a new approach to the objective estimation of perceived speech quality. This new approach uses a simple but effective perceptual transformation and a distance measure that consists of a hierarchy of measuring normalizing blocks. Each measuring normalizing block integrates two perceptually transformed signals over some time or frequency interval to determine the average difference across that interval. This difference is then normalized out of one signal, and is further processed to generate one or more measurements. In this part, the resulting estimates of the perceived speech quality are correlated with the results of nine subjective listening tests. Together, these tests include 219 4 kHz bandwidth speech codecs, transmission systems, and reference conditions, with bit rates ranging from 2.4 to 61 kb/s. When compared with six other estimators, significant improvements are seen in many cases, particularly at lower bit rates, and when bit errors or frame erasures are present. These hierarchical structures of measuring normalizing blocks, or other structures of measuring normalizing blocks may also address open issues in perceived audio quality estimation, layered speech or audio coding, automatic speech or speaker recognition, audio signal enhancement, and other areas.