Andreas Spanias
Arizona State University
Signal processingAlgorithmMachine learningEngineeringSpeech codingArtificial intelligencePattern recognitionElectronic engineeringWireless sensor networkSoftwareSpeech recognitionMathematicsComputer scienceMultimediaFeature extractionJavaSpeech processingCluster analysisReal-time computingDigital signal processing
495Publications
32H-index
5,941Citations
Publications 472
Newest
#1Kristen JaskieH-Index: 3
#2Joshua P. MartinH-Index: 9
Last. Andreas SpaniasH-Index: 32
view all 0 authors...
Source
Jun 6, 2021 in ICASSP (International Conference on Acoustics, Speech, and Signal Processing)
#1Vivek Sivaraman Narayanaswamy (ASU: Arizona State University)H-Index: 3
#2Jayaraman J. Thiagarajan (LLNL: Lawrence Livermore National Laboratory)H-Index: 19
Last. Andreas Spanias (ASU: Arizona State University)H-Index: 32
view all 3 authors...
Through the use of carefully tailored convolutional neural network architectures, a deep image prior (DIP) can be used to obtain pre-images from latent representation encodings. Though DIP inversion has been known to be superior to conventional regularized inversion strategies such as total variation, such an over-parameterized generator is able to effectively reconstruct even images that are not in the original data distribution. This limitation makes it challenging to utilize such priors for t...
Source
#1Vivek Sivaraman Narayanaswamy (ASU: Arizona State University)H-Index: 3
#2Jayaraman J. Thiagarajan (LLNL: Lawrence Livermore National Laboratory)H-Index: 19
Last. Andreas Spanias (ASU: Arizona State University)H-Index: 32
view all 3 authors...
Unsupervised deep learning methods for solving audio restoration problems extensively rely on carefully tailored neural architectures that carry strong inductive biases for defining priors in the time or spectral domain. In this context, lot of recent success has been achieved with sophisticated convolutional network constructions that recover audio signals in the spectral domain. However, in practice, audio priors require careful engineering of the convolutional kernels to be effective at solvi...
With increased interest in adopting AI methods for clinical diagnosis, a vital step towards safe deployment of such tools is to ensure that the models not only produce accurate predictions but also do not generalize to data regimes where the training data provide no meaningful evidence. Existing approaches for ensuring the distribution of model predictions to be similar to that of the true distribution rely on explicit uncertainty estimators that are inherently hard to calibrate. In this paper, ...
Sampling one or more effective solutions from large search spaces is a recurring idea in machine learning (ML), and sequential optimization has become a popular solution. Typical examples include data summarization, sample mining for predictive modeling, and hyperparameter optimization. Existing solutions attempt to adaptively trade off between global exploration and local exploitation, in which the initial exploratory sample is critical to their success. While discrepancy-based samples have bec...
Source
Massive MIMO is a key component of current and future wireless communication systems. To harvest the multiplexing and beamforming gains of these large-scale MIMO systems, however, the channel knowledge needs to be acquired at the massive MIMO transmitters. This is typically associated with large training overhead, especially in FDD massive MIMO. Recent research showed that deep learning could lead to interesting gains for massive MIMO systems by mapping the channel knowledge from the uplink to d...
2 CitationsSource
Oct 25, 2020 in INTERSPEECH (Conference of the International Speech Communication Association)
#1Vivek Sivaraman Narayanaswamy (ASU: Arizona State University)H-Index: 3
#2Jayaraman J. Thiagarajan (LLNL: Lawrence Livermore National Laboratory)H-Index: 19
Last. Andreas Spanias (ASU: Arizona State University)H-Index: 32
view all 4 authors...
State-of-the-art under-determined audio source separation systems rely on supervised end-end training of carefully tailored neural network architectures operating either in the time or the spectral domain. However, these methods are severely challenged in terms of requiring access to expensive source level labeled data and being specific to a given set of sources and the mixing process, which demands complete re-training when those assumptions change. This strongly emphasizes the need for unsupe...
Source
#1Jayaraman J. Thiagarajan (LLNL: Lawrence Livermore National Laboratory)H-Index: 19
#2Deepta Rajan (IBM)H-Index: 6
Last. Andreas Spanias (ASU: Arizona State University)H-Index: 32
view all 4 authors...
Effective patient care mandates rapid, yet accurate, diagnosis. With the abundance of non-invasive diagnostic measurements and electronic health records (EHR), manual interpretation for differential diagnosis has become time-consuming and challenging. This has led to wide-spread adoption of AI-powered tools, in pursuit of improving accuracy and efficiency of this process. While the unique challenges presented by each modality and clinical task demand customized tools, the cumbersome process of m...
1 CitationsSource
Oct 1, 2020 in ICIP (International Conference on Image Processing)
Last. Suren Jayasuriya (ASU: Arizona State University)H-Index: 9
view all 7 authors...
Image sensors with programmable region-of-interest (ROI) readout are a new sensing technology important for energyefficient embedded computer vision. In particular, ROIs can subsample the number of pixels being readout while performing single object tracking in a video. In this paper, we develop adaptive sampling algorithms which perform joint object tracking and predictive video subsampling. We utilize an object detection consisting of either mean shift tracking or a neural network, coupled wit...
Source
#1Uday Shankar Shanthamallu (ASU: Arizona State University)H-Index: 4
#2Jayaraman J. Thiagarajan (LLNL: Lawrence Livermore National Laboratory)H-Index: 19
Last. Andreas Spanias (ASU: Arizona State University)H-Index: 32
view all 4 authors...
Modern data analysis pipelines are becoming increasingly complex due to the presence of multiview information sources. While graphs are effective in modeling complex relationships, in many scenarios, a single graph is rarely sufficient to succinctly represent all interactions, and hence, multilayered graphs have become popular. Though this leads to richer representations, extending solutions from the single-graph case is not straightforward. Consequently, there is a strong need for novel solutio...
5 CitationsSource