相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article
Computer Science, Artificial Intelligence
Farhad Pourpanah et al.
Summary: Generalized zero-shot learning (GZSL) trains a model to classify data samples when some output classes are unknown. Semantic information of seen and unseen classes is used to bridge the gap between them. This review paper provides an overview, discusses categorization and representative methods, benchmark datasets, applications, and research gaps of GZSL.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Acoustics
Fengyan An et al.
Summary: This paper addresses the feedforward controller design problem using cascade biquad filters for active noise control headphones, and proposes criterion functions for evaluating comprehensive noise reduction performance. Experimental results show that the comprehensive performance under multiple directions can be significantly improved when multiple reference microphones are used along with a multi-channel control strategy.
Article
Engineering, Electrical & Electronic
Daocheng Chen et al.
Summary: This letter proposes a secondary path-decoupled ANC algorithm based on deep learning, which generates control signals by optimizing an adaptive filter to eliminate noise.
IEEE SIGNAL PROCESSING LETTERS
(2022)
Article
Engineering, Electrical & Electronic
Dongyuan Shi et al.
Summary: This study proposes an optimal penalty factor and its estimation method for achieving the optimal solution of the minimum output variance filtered reference least mean square (MOV-FxLMS) algorithm under the target output-variance constraint.
IEEE SIGNAL PROCESSING LETTERS
(2022)
Article
Engineering, Electrical & Electronic
Dongyuan Shi et al.
Summary: Fixed-filter strategy is crucial in active noise control, but it cannot achieve optimal noise reduction for different noise types. A selective fixed-filter ANC method based on 2D CNN is proposed to derive the most suitable control filter for different noise types, reducing classification complexity.
Article
Acoustics
Feiran Yang
Summary: This paper studies the convergence behavior of partitioned-block frequency-domain adaptive filters (PBFDAF) under under-modeling scenarios. Stochastic analysis is carried out for both constrained and unconstrained algorithms individually to account for their convergence differences. By transforming the frequency-domain error vectors and update equations into time-domain counterparts, the convergence behavior of the augmented weight-error vector can be analyzed completely. The mean and mean-square convergence behavior, as well as the learning curve and steady-state solutions, are presented. The theoretical model provides new insights into the convergence behavior of deficient-length PBFDAF algorithms, which are well supported by computer simulations.
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
(2022)
Article
Computer Science, Information Systems
Xiaoyi Shen et al.
Summary: Active Noise Control (ANC) headphones are used to create quiet zones by capturing ambient noise and generating anti-noise, while wireless ANC systems utilize reference microphones and wireless communication to enhance noise reduction performance. This study implemented a multi-channel feedforward wireless ANC system and proposed a coherence-based weight determination algorithm to improve noise reduction efficacy in headphones, validated through numerical simulations and real-time experiments.
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY
(2022)
Article
Engineering, Electrical & Electronic
Chong-Rui Huang et al.
Summary: Hear-through (HT) technique actively compensates for passive isolation in headphones by enhancing the perception of ambient sound. It generates artificial sound based on a relative transfer function (RTF) to make up for the loss of ambient sound. This study introduces a time-shift scheme and an active equalization algorithm to accurately calculate the compensating sound.
IEEE TRANSACTIONS ON CONSUMER ELECTRONICS
(2022)
Review
Chemistry, Multidisciplinary
Jun Yang et al.
Summary: Sound field control technology enables the active management of audio in an acoustical environment, including sound field reproduction, personal audio systems, and active noise control. This paper briefly reviews the advances of these three types of techniques and discusses their algorithms and applications.
APPLIED SCIENCES-BASEL
(2022)
Article
Engineering, Mechanical
Zeqiang Zhang et al.
Summary: PVSM is a robust virtual sensing method for multichannel adaptive feedback ANC systems, which outperforms AFM and RMM, effectively reducing varying narrowband noises.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Proceedings Paper
Acoustics
Kazuyuki Arikawa et al.
Summary: This paper proposes a spatial active noise control method based on individual interpolation of primary and secondary sound fields, which outperforms the method based on total kernel interpolation according to experimental results.
2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
(2022)
Article
Acoustics
Han Wang et al.
Summary: This study analyzes the performance degradation of the narrowband active noise control algorithm under frequency interference effects and obtains theoretical results regarding the convergence process, noise reduction value, stability condition, and optimum step size. The research finds that tones with large frequency difference can converge independently while systems with close frequencies experience a slower convergence rate.
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
(2022)
Article
Engineering, Electrical & Electronic
Zhengding Luo et al.
Summary: This paper proposes a hybrid SFANC-FxNLMS approach that combines a one-dimensional convolutional neural network (1D CNN) and an adaptive algorithm, achieving fast response time, low noise reduction error, and high robustness in noise control.
IEEE SIGNAL PROCESSING LETTERS
(2022)
Article
Acoustics
Xander Pike et al.
JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA
(2021)
Article
Construction & Building Technology
Bhan Lam et al.
Summary: Urban noise pollution poses a significant threat to public health that has been often overlooked. Despite the benefits seen in applications like automobiles, active noise control in the built environment remains uncommon. The development of active noise control solutions for buildings is gaining traction, but there are still challenges to widespread adoption.
BUILDING AND ENVIRONMENT
(2021)
Article
Engineering, Mechanical
Dongyuan Shi et al.
Summary: Multichannel active noise control (MCANC) is an effective solution for achieving large noise-cancellation areas in complicated acoustic fields, but the computational complexity of MCANC algorithms has been a challenge. The proposed BCD McFxLMS algorithm reduces computation costs while maintaining noise reduction performance, and integrates a momentum mechanism to improve convergence speed. Simulation and experimental results demonstrate the effectiveness of the proposed algorithms in realistic environments.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Hao Zhang et al.
Summary: This paper proposes a deep learning method - deep ANC to address the nonlinear ANC problem, by training CRN to estimate the spectrogram of the canceling signal, achieving active noise cancellation, and introducing a delay-compensated strategy to solve the latency problem.
Review
Engineering, Electrical & Electronic
Lu Lu et al.
Summary: This paper focuses on the development of ANC techniques over the past decade, including the research on linear ANC algorithms and nonlinear ANC techniques. It also summarizes novel methods and applications of ANC emerging in the past decade, and discusses future research challenges regarding the ANC technique.
Article
Chemistry, Multidisciplinary
Jan Sikora et al.
Summary: This study focuses on testing the quality of manufactured products based on their sound expression, and finds that a high level of environmental noise significantly impacts the decline in classification accuracy of the decision-making algorithm.
APPLIED SCIENCES-BASEL
(2021)
Article
Acoustics
Junqing Zhang et al.
Summary: The study proposes using higher-order variable-directivity sound sources as secondary sources for spatial active noise control, aiming to effectively cancel noise in time-varying room environments by controlling both interior and exterior sound fields. The method approximates free-field propagation through pre-calibration to adapt to noise variations and achieve acceptable levels of exterior sound field control.
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
(2021)
Proceedings Paper
Acoustics
Xiaoyi Shen et al.
Summary: This study investigates the use of a wireless reference microphone to capture signals around noise sources, and proposes a coherence-based selection algorithm to improve the quality of the reference signals, demonstrating its advantages in effectiveness.
2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021)
(2021)
Proceedings Paper
Acoustics
Yuan-Kuei Wu et al.
Summary: The paper proposes applying meta-learning to the task of speech separation to quickly adapt to new speakers. Experimental results show that the model can adapt to new speakers and noisy environments, while revealing the roles of the encoder and decoder in feature-reuse.
2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021)
(2021)
Article
Acoustics
Shoichi Koyama et al.
Summary: A novel active noise control method based on kernel interpolation of sound field is proposed in this study, which allows for flexible array configurations and improved accuracy in sound field estimation. Experimental results show that the proposed method outperforms traditional multipoint pressure control methods in reducing regional noise levels.
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
(2021)
Article
Acoustics
Dongyuan Shi et al.
Summary: The paper introduces a QCQP-based algorithm to address output saturation in adaptive systems, employing an LMS algorithm with an optimal leak factor. However, this method is only applicable when the statistical features of the control signal are known, prompting the incorporation of adaptive inverse modeling technique for practical estimation of the optimal leaky factor.
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
(2021)
Article
Computer Science, Hardware & Architecture
Dongyuan Shi et al.
IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS
(2020)
Article
Acoustics
Shulin Wen et al.
JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA
(2020)
Article
Acoustics
Feiran Yang et al.
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
(2020)
Article
Acoustics
Dongyuan Shi et al.
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
(2020)
Article
Acoustics
Krzysztof Mazur et al.
Article
Chemistry, Multidisciplinary
Jihui Zhang et al.
APPLIED SCIENCES-BASEL
(2019)
Article
Computer Science, Artificial Intelligence
Jiuxiang Gu et al.
PATTERN RECOGNITION
(2018)
Review
Chemistry, Multidisciplinary
Feiran Yang et al.
APPLIED SCIENCES-BASEL
(2018)
Article
Computer Science, Hardware & Architecture
Cheng-Yuan Chang et al.
IEEE CONSUMER ELECTRONICS MAGAZINE
(2016)
Article
Engineering, Mechanical
Jordan Cheer et al.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2015)
Article
Engineering, Electrical & Electronic
Dennis R. Morgan
IEEE SIGNAL PROCESSING MAGAZINE
(2013)
Article
Engineering, Electrical & Electronic
Yoshinobu Kajikawa et al.
APSIPA TRANSACTIONS ON SIGNAL AND INFORMATION PROCESSING
(2012)
Article
Acoustics
M Pawelczyk