Building recurrent networks by unfolding iterative thresholding for sequential sparse recovery

Wisdom, Scott; Powers, Thomas A.; Pitton, J.W.; Atlas, Les

doi:10.1109/icassp.2017.7952977

Cited by 30 publications

(30 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…x ∈ R 128 where the non-zero elements are sampled from N (0, 1). Furthermore, we fix the total number of layers of the decoder function to L = 30; equivalent of performing only 30 optimization iterations of the form ( 20), ( 22), (26), and (27). As for the sensing matrix (to be learned), we assume Φ ∈ R 512×128 .…”

Section: Numerical Resultsmentioning

confidence: 99%

Model-Aware Deep Architectures for One-Bit Compressive Variational Autoencoding

Khobahi,

Soltanalian

2019

Preprint

View full text Add to dashboard Cite

Parameterized mathematical models play a central role in understanding and design of complex information systems. However, they often cannot take into account the intricate interactions innate to such systems. On the contrary, purely datadriven approaches do not need explicit mathematical models for data generation and have a wider applicability at the cost of interpretability. In this paper, we consider the design of a one-bit compressive variational autoencoder, and propose a novel hybrid model-based and data-driven methodology that allows us not only to design the sensing matrix and the quantization thresholds for one-bit data acquisition, but also allows for learning the latent-parameters of iterative optimization algorithms specifically designed for the problem of one-bit sparse signal recovery. In addition, the proposed method has the ability to adaptively learn the proper quantization thresholds, paving the way for amplitude recovery in one-bit compressive sensing. Our results demonstrate a significant improvement compared to state-of-the-art modelbased algorithms.

show abstract

Section: Numerical Resultsmentioning

confidence: 99%

Model-Aware Deep Architectures for One-Bit Compressive Variational Autoencoding

Khobahi,

Soltanalian

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Moreover, the performance achieved by CASA-based methods tends to be affected by multipitch estimation for its dependence on pitch Over the past few years, with the development of deep learning, researchers have suggested that the nonlinear processing and feature learning capabilities of deep models exhibit significant advantages in solving speech separation problems. For this reason, many models using deep learning for speech separation have been proposed (e.g., Deep Neural Network (DNN), deep stacking, Deep Stack Neural Network (DSN) [45], and other efficient deep learning models [46][47][48][49][50]). In addition, numerous deep learning algorithms have been proposed for single-channel speech separation [51][52][53][54].…”

Section: Related Workmentioning

confidence: 99%

An Improved Unsupervised Single‐Channel Speech Separation Algorithm for Processing Speech Sensor Signals

Jiang

Lin

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

As network supporting devices and sensors in the Internet of Things are leaping forward, countless real-world data will be generated for human intelligent applications. Speech sensor networks, an important part of the Internet of Things, have numerous application needs. Indeed, the sensor data can further help intelligent applications to provide higher quality services, whereas this data may involve considerable noise data. Accordingly, speech signal processing method should be urgently implemented to acquire low-noise and effective speech data. Blind source separation and enhancement technique refer to one of the representative methods. However, in the unsupervised complex environment, in the only presence of a single-channel signal, many technical challenges are imposed on achieving single-channel and multiperson mixed speech separation. For this reason, this study develops an unsupervised speech separation method CNMF+JADE, i.e., a hybrid method combined with Convolutional Non-Negative Matrix Factorization and Joint Approximative Diagonalization of Eigenmatrix. Moreover, an adaptive wavelet transform-based speech enhancement technique is proposed, capable of adaptively and effectively enhancing the separated speech signal. The proposed method is aimed at yielding a general and efficient speech processing algorithm for the data acquired by speech sensors. As revealed from the experimental results, in the TIMIT speech sources, the proposed method can effectively extract the target speaker from the mixed speech with a tiny training sample. The algorithm is highly general and robust, capable of technically supporting the processing of speech signal acquired by most speech sensors.

show abstract

“…1(b)] in comparison with the soft-thresholding operator φ γ (u) [see Fig. 1(a)], which is used in SISTA [15].…”

Section: -1 Minimization In Sequential Signal Recoverymentioning

confidence: 99%

“…We apply the proposed model in the problem of video reconstruction from low-dimensional measurements, that is, sequential frame compressed sensing. Experimentation on the moving MNIST dataset 1 [17] shows that the proposed model achieves higher reconstruction results compared to various state-of-the-art RNN models, including SISTA-RNN [15].…”

Section: Introductionmentioning

confidence: 99%

Designing Recurrent Neural Networks by Unfolding an L1-L1 Minimization Algorithm

Lê

Luong

Deligiannis

2019

2019 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

We propose a new deep recurrent neural network (RNN) architecture for sequential signal reconstruction. Our network is designed by unfolding the iterations of the proximal gradient method that solves the 1 -1 minimization problem. As such, our network leverages by design that signals have a sparse representation and that the difference between consecutive signal representations is also sparse. We evaluate the proposed model in the task of reconstructing video frames from compressive measurements and show that it outperforms several state-of-the-art RNN models.Index Terms-Sparse signal recovery, deep unfolding, recurrent neural networks, 1 -1 minimization.

show abstract

Building recurrent networks by unfolding iterative thresholding for sequential sparse recovery

Cited by 30 publications

References 20 publications

Model-Aware Deep Architectures for One-Bit Compressive Variational Autoencoding

Model-Aware Deep Architectures for One-Bit Compressive Variational Autoencoding

An Improved Unsupervised Single‐Channel Speech Separation Algorithm for Processing Speech Sensor Signals

Designing Recurrent Neural Networks by Unfolding an L1-L1 Minimization Algorithm

Contact Info

Product

Resources

About