Presents corrections to the article “ARAUS: A Large-Scale Dataset and Baseline Models of Affective Responses to Augmented Urban Soundscapes”.

Choosing optimal maskers for existing soundscapes to effect a desired perceptual change via soundscape augmentation is non-trivial due to extensive varieties of maskers and a dearth of benchmark datasets with which to compare and develop soundscape augmentation models. To address this problem, we make publicly available the ARAUS (Affective Responses to Augmented Urban Soundscapes) dataset, which comprises a five-fold cross-validation set and independent test set totaling 25,440 unique subjective perceptual responses to augmented soundscapes presented as audio-visual stimuli. Each augmented soundscape is made by digitally adding “maskers” (bird, water, wind, traffic, construction, or silence) to urban soundscape recordings at fixed soundscape-to-masker ratios. Responses were then collected by asking participants to rate how pleasant, annoying, eventful, uneventful, vibrant, monotonous, chaotic, calm, and appropriate each augmented soundscape was, in accordance with ISO/TS 12913-2:2018. Participants also provided relevant demographic information and completed standard psychological questionnaires. We perform exploratory and statistical analysis of the responses obtained to verify internal consistency and agreement with known results in the literature. Finally, we demonstrate the benchmarking capability of the dataset by training and comparing four baseline models for urban soundscape pleasantness: a low-parameter regression model, a high-parameter convolutional neural network, and two attention-based networks in the literature.

The remote microphone technique (RMT) is often used in active noise control (ANC) applications to overcome design constraints in microphone placements by estimating the acoustic pressure at inconvenient locations using a pre-calibrated observation filter (OF), albeit limited to stationary primary acoustic fields. While the OF estimation in varying primary fields can be significantly improved through the recently proposed source decomposition technique, it requires knowledge of the relative source strengths between incoherent primary noise sources. This paper proposes a method for combining the RMT with a new source-localization technique to estimate the source ratio parameter. Unlike traditional source-localization techniques, the proposed method is capable of being implemented in a real-time RMT application. Simulations with measured responses from an open-aperture ANC application showed a good estimation of the source ratio parameter, which allows the observation filter to be modelled in real-time.

Autonomous soundscape augmentation systems typically use trained models to pick optimal maskers to effect a desired perceptual change. While acoustic information is paramount to such systems, contextual information, including participant demographics and the visual environment, also influences acoustic perception. Hence, we propose modular modifications to an existing attention-based deep neural network, to allow early, mid-level, and late feature fusion of participant-linked, visual, and acoustic features. Ablation studies on module configurations and corresponding fusion methods using the ARAUS dataset show that contextual features improve the model performance in a statistically significant manner on the normalized ISO Pleasantness, to a mean squared error of 0.1194±0.0012 for the best-performing all-modality model, against 0.1217±0.0009 for the audio-only model. Soundscape augmentation systems can thereby leverage multimodal inputs for improved performance. We also investigate the impact of individual participant-linked factors using trained models to illustrate improvements in model explainability.

Practical Active Noise Control (ANC) systems typically require a restriction in their maximum output power, to prevent overdriving the loudspeaker and causing system instability. Recently, the minimum output variance filtered-reference least mean square (MOV-FxLMS) algorithm was shown to have optimal control under output constraint with an analytically formulated penalty factor, but it needs offline knowledge of disturbance power and secondary path gain. The constant penalty factor in MOV-FxLMS is also susceptible to variations in disturbance power that could cause output power constraint violations. This paper presents a new variable penalty factor that utilizes the estimated disturbance in the established Modified-FxLMS (MFxLMS) algorithm, resulting in a computationally efficient MOV-MFxLMS algorithm that can adapt to changes in disturbance levels in real-time. Numerical simulation with real noise and plant response showed that the variable penalty factor always manages to meet its maximum power output constraint despite sudden changes in disturbance power, whereas the fixed penalty factor has suffered from a constraint mismatch.

Practical active noise control (ANC) systems, like the active noise cancellation headphone, usually adopt a control filter with preset coefficients to achieve satisfactory noise reduction performance for dynamic noise and higher robustness. In this strategy, selecting the appropriate control filter for different types of noise is critical to the noise cancellation performance, and this selection mechanism is typically determined by trial and error. Hence, this article proposes a computation-efficient one-dimensional convolutional neural network capable of selecting the most suitable pre-trained control filter for each distinct primary noise. Applying the similarity matching method allows the proposed model to have a better generalization and can even deal with zero-shot noise, whose class does not exist in the training set. The Large-margin softmax (L-softmax) is also investigated to improve the proposed model's performance. Furthermore, when dealing with the N-shot learning problem, where there are few known real-world noise samples for the ANC system, an additional fine-tuning strategy is used to improve control filter selection accuracy. Numerical simulations on measured primary and secondary paths validate the proposed method's efficacy.

Due to their computational efficiency, least mean square (LMS)–based algorithms are still widely utilized to achieve optimal control in active noise control (ANC) applications. Real-world implementation of advanced ANC functionalities, such as selective cancellation of frequencies, is nonetheless hampered by complexity trade-offs, especially with computationally-expensive frequency-domain approaches. Prevailing time-domain adaptive algorithms – proposed to alleviate complexities from transformation – continue to incur increased complexities while constraining the magnitude of frequency bins in the time-domain filters. To address existing complexities in time-domain approaches, this paper proposes a circulant convolutional penalty factor that assists the extended leaky filtered-reference LMS (FxLMS) algorithm in achieving frequency constraint without any frequency-domain transform. This circulant convolutional penalty factor is readily determined by methods for designing finite response filters, such as frequency sampling. Additionally, the coordinate descent method is adopted to further reduce the proposed algorithm's computations, significantly increasing its feasibility for implementation on conventional real-time processors. Finally, the numerical simulations performed on the measured primary and secondary paths demonstrate the effectiveness of the proposed algorithm.

Soundscape augmentation, which involves the addition of sounds known as "maskers" to a given soundscape, is a human-centric urban noise mitigation measure aimed at improving the overall sound-scape quality. However, the choice of maskers is often predicated on laborious processes and is inflexible to the time-varying nature of real-world soundscapes. Owing to the perceptual uniqueness of each soundscape and the inherent subjectiveness of human perception, we propose a probabilistic perceptual attribute predictor (PPAP) that predicts parameters of random distributions as outputs instead of a single deterministic value. Using the PPAP, we developed a novel automatic masker selection system (AMSS), which selects optimal masker candidates based on the predicted distribution of the ISO 12913-3 Pleasantness score for a given soundscape. Via a largescale listening test with 300 participants, we collected 12600 subjective responses, each to a unique augmented soundscape, to train the PPAP models in a 5-fold cross-validation scheme. Using a convolutional recurrent neural network backbone and experimenting with several variants of the attention mechanism for the PPAP, we evaluated the proposed system on a blind test set with 48 unseen augmented soundscapes to assess the effectiveness of the probabilistic output scheme over traditional deterministic systems.

The minimum output variance filtered reference least mean square (MOV-FxLMS) algorithm is a effective algorithm that utilizes the penalty mechanism to help the active noise control (ANC) system achieve noise cancellation with constrained output variance or power. As it can constrain output power, the MOV-FxLMS algorithm can freely determine the ANC system’s control effort, avoiding output saturation, and improving system stability. However, its performance is determined by a penalty factor, which is normally chosen by trial and error. Hence, this work proposes an optimal penalty factor and its feasible estimation that does not require any assumptions of Gaussian reference signal or input independence. This factor assists the MOV-FxLMS in achieving the optimal solution under the target output-variance constraint. Numerical simulations on measured paths demonstrate its effectiveness for various types of noise.

The selection of maskers and playback gain levels in an in-situ soundscape augmentation system is crucial to its effectiveness in improving the overall acoustic comfort of a given environment. Traditionally, the selection of appropriate maskers and gain levels has been informed by expert opinion, which may not be representative of the target population, or by listening tests, which can be time- and labor-intensive. Furthermore, the resulting static choices of masker and gain are often inflexible to dynamic real-world soundscapes. In this work, we utilized a deep learning model to perform joint selection of the optimal masker and its gain level for a given soundscape. The proposed model was designed with highly modular building blocks, allowing for an optimized inference process that can quickly search through a large number of masker-gain combinations. In addition, we introduced the use of feature-domain soundscape augmentation conditioned on the digital gain level, eliminating the computationally expensive waveform-domain mixing process during inference, as well as the tedious gain adjustment process required for new maskers. The proposed system was evaluated on a large-scale dataset of subjective responses to augmented soundscapes with 442 participants, with the best model achieving a mean squared error of${0.122}\mathbf {\pm }{0.005}$on pleasantness score, validating the ability of the model to predict combined effect of the masker and its gain level on the perceptual pleasantness level. The proposed system thus allows in-situ or mixed-reality soundscape augmentation to be performed autonomously with near real-time latency while continuously accounting for changes in acoustic environments.

With the advent of efficient low-cost processors and electroacoustic components, there is renewed interest in the practical implementation of active noise control (ANC). However, the slow convergence of conventional adaptive algorithms deployed in ANC restricts its handling of typical amplitude-varying noise. Hence, we proposed a modified model-agnostic, meta-learning (MAML) strategy to obtain an initial control filter, which accelerates an adaptive algorithm's convergence when dealing with different types of amplitude-varying low-frequency noise. Numerical simulations with measured paths and real noise sources demonstrate its convergence acceleration efficacy in practical scenarios.

Output saturation, mainly caused by the power amplifier, is a critical issue influencing the performance and stability of an adaptive system, such as in active noise control. In this paper, a quadratically constrained quadratic program (QCQP) is defined to achieve optimal control under the averaging-output-power constraint, which ensures the output of the system operates linearly and hence, avoids the output saturation. To solve this QCQP problem recursively in practice, this paper utilizes one of the leaky-based filtered-x least mean square algorithm with an optimal leak factor. However, this method only can be applied when the statistical feature of the control signal with maximum output-power is known, which is difficult to obtain in practice. Hence, by incorporating the adaptive inverse modeling technique, we can derive a practical estimation of the optimal leaky factor, which is applicable to different noise types. Furthermore, as the optimal output-constraint control forces the output to operate linearly, the nonlinear amplifier model is not required for the leak factor estimate. The simulation of the proposed algorithm is carried out on measured nonlinear paths to validate its efficacy.

Active noise control is an efficient approach in dealing with unwanted acoustic disturbances. However, most of the active noise control algorithms aim to control the signal of the error sensor leading to local noise attenuation only around the error microphones. One of the approaches to enlarge the quiet zone is by restraining the derivative of the sound field around the error microphone to zero. It achieves noise cancellation not only at the error microphone but also in its vicinity. This paper proposes a time-domain adaptive algorithm to implement the spatial derivative constraint, which avoids the complex analytic acoustic calculations. Furthermore, the proposed algorithm does not require extra microphones to acquire the sound field information during control. Numerical simulations are carried out to validate the effectiveness of the proposed method.

Conventional real-time active noise control (ANC) usually employs the adaptive filtered-x least mean square (FxLMS) algorithm to approach optimum coefficients for the control filter. However, lengthy training is usually required, and the perceived noise reduction is not immediately realized. Motivated by the practical implementation, we propose a selective fixed-filter active noise control (SFANC) algorithm, which selects a pretrained control filter to attenuate the detected primary noise rapidly. On top of improved robustness, the complexity analysis reveals that SFANC appears to be more efficient. The SFANC algorithm chooses the most suitable control filter based on the frequency-band-match approach implemented in a partitioned frequency-domain filter. Through simulations, SFANC is shown to exhibit a satisfactory response time and steady-state noise reduction performance, even for time-varying noise and real non-stationary disturbance.

Multichannel active noise control (MCANC) is widely recognized as an effective and efficient solution for acoustic noise and vibration cancellation, such as in high-dimensional ventilation ducts, open windows, and mechanical structures. The feedforward multichannel filtered-x least mean square (FFMCFxLMS) algorithm is commonly used to dynamically adjust the transfer function of the multichannel controllers for different noise environments. The computational load incurred by the FFMCFxLMS algorithm, however, increases exponentially with increasing channel count, thus requiring high-end field-programmable gate array (FPGA) processors. Nevertheless, such processors still need specific configurations to cope with soaring computing loads as the channel count increases. To achieve a high-efficiency implementation of the FFMCFxLMS algorithm with floating-point arithmetic, a novel architecture based on multiple-parallel-branch with folding (MPBF) technique is proposed. This architecture parallelizes the branches and reuses the multiplier and adder in each folded branch so that the tradeoff between throughput and the usage of the hardware resources is balanced. The proposed architecture is validated in an experimental setup that implements the FFMCFxLMS algorithm for the MCANC system with 24 reference sensors, 24 secondary sources, and 24 error sensors, at a sampling and throughput rates of 25 kHz and 260 Mb/s, respectively.

This paper revisits the virtual sensing active noise control (VS-ANC) technique and extends it to a general multichannel ANC (MCANC) implementation. A frequency domain analysis shows that the multichannel virtual sensing ANC (VS-MCANC) technique arrives at an optimal control filter to cancel the noise disturbance at the virtual locations and overcomes the spatial correlation and causality constraints between the physical microphone and the virtual microphone. A real-time control of broadband noise with a 4-channel VS-MCANC implemented in a test chamber validates its theoretical analysis and demonstrates its active control effectiveness.

The leaky filtered-input least mean square (LFxLMS) algorithm is widely used in active noise control applications to minimize the degradation of attenuation performance due to output saturation distortion. However, the leak factor, which is critical in determining the steady-state error and robustness of the algorithm, is usually selected through trial and error. This letter proposes a leak factor selection approach, which ensures the LFxLMS algorithm converges to its optimal solution under the average-output-power constraint and can be readily derived in practice. Both broadband and narrowband cases are considered in the derivation without the independence assumption, and the simulations are conducted based on real primary and secondary paths to verify its effectiveness.

Selective active noise control (SANC) is a method to select a pre-trained control filter for different primary noises, instead of using conventional real-time computation of the control filter coefficients. SANC has the advantage of improving the robustness of control filter while reducing the computational complexity. This paper presents a practical strategy in choosing a suitable control filter based on the frequency-band-match mechanism implemented in a partitioned frequency domain filter structure. Both simulation and real-time experiment are carried out validate the noise reduction performance of the SANC compared to the conventional FxLMS algorithm.