Matching Items (15)
Filtering by
- All Subjects: artificial intelligence
- Creators: Turaga, Pavan
Description
Following the success in incorporating perceptual models in audio coding algorithms, their application in other speech/audio processing systems is expanding. In general, all perceptual speech/audio processing algorithms involve minimization of an objective function that directly/indirectly incorporates properties of human perception. This dissertation primarily investigates the problems associated with directly embedding an auditory model in the objective function formulation and proposes possible solutions to overcome high complexity issues for use in real-time speech/audio algorithms. Specific problems addressed in this dissertation include: 1) the development of approximate but computationally efficient auditory model implementations that are consistent with the principles of psychoacoustics, 2) the development of a mapping scheme that allows synthesizing a time/frequency domain representation from its equivalent auditory model output. The first problem is aimed at addressing the high computational complexity involved in solving perceptual objective functions that require repeated application of auditory model for evaluation of different candidate solutions. In this dissertation, a frequency pruning and a detector pruning algorithm is developed that efficiently implements the various auditory model stages. The performance of the pruned model is compared to that of the original auditory model for different types of test signals in the SQAM database. Experimental results indicate only a 4-7% relative error in loudness while attaining up to 80-90 % reduction in computational complexity. Similarly, a hybrid algorithm is developed specifically for use with sinusoidal signals and employs the proposed auditory pattern combining technique together with a look-up table to store representative auditory patterns. The second problem obtains an estimate of the auditory representation that minimizes a perceptual objective function and transforms the auditory pattern back to its equivalent time/frequency representation. This avoids the repeated application of auditory model stages to test different candidate time/frequency vectors in minimizing perceptual objective functions. In this dissertation, a constrained mapping scheme is developed by linearizing certain auditory model stages that ensures obtaining a time/frequency mapping corresponding to the estimated auditory representation. This paradigm was successfully incorporated in a perceptual speech enhancement algorithm and a sinusoidal component selection task.
ContributorsKrishnamoorthi, Harish (Author) / Spanias, Andreas (Thesis advisor) / Papandreou-Suppappola, Antonia (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Tsakalis, Konstantinos (Committee member) / Arizona State University (Publisher)
Created2011
Description
Digital sound synthesis allows the creation of a great variety of sounds. Focusing on interesting or ecologically valid sounds for music, simulation, aesthetics, or other purposes limits the otherwise vast digital audio palette. Tools for creating such sounds vary from arbitrary methods of altering recordings to precise simulations of vibrating objects. In this work, methods of sound synthesis by re-sonification are considered. Re-sonification, herein, refers to the general process of analyzing, possibly transforming, and resynthesizing or reusing recorded sounds in meaningful ways, to convey information. Applied to soundscapes, re-sonification is presented as a means of conveying activity within an environment. Applied to the sounds of objects, this work examines modeling the perception of objects as well as their physical properties and the ability to simulate interactive events with such objects. To create soundscapes to re-sonify geographic environments, a method of automated soundscape design is presented. Using recorded sounds that are classified based on acoustic, social, semantic, and geographic information, this method produces stochastically generated soundscapes to re-sonify selected geographic areas. Drawing on prior knowledge, local sounds and those deemed similar comprise a locale's soundscape. In the context of re-sonifying events, this work examines processes for modeling and estimating the excitations of sounding objects. These include plucking, striking, rubbing, and any interaction that imparts energy into a system, affecting the resultant sound. A method of estimating a linear system's input, constrained to a signal-subspace, is presented and applied toward improving the estimation of percussive excitations for re-sonification. To work toward robust recording-based modeling and re-sonification of objects, new implementations of banded waveguide (BWG) models are proposed for object modeling and sound synthesis. Previous implementations of BWGs use arbitrary model parameters and may produce a range of simulations that do not match digital waveguide or modal models of the same design. Subject to linear excitations, some models proposed here behave identically to other equivalently designed physical models. Under nonlinear interactions, such as bowing, many of the proposed implementations exhibit improvements in the attack characteristics of synthesized sounds.
ContributorsFink, Alex M (Author) / Spanias, Andreas S (Thesis advisor) / Cook, Perry R. (Committee member) / Turaga, Pavan (Committee member) / Tsakalis, Konstantinos (Committee member) / Arizona State University (Publisher)
Created2013
Description
Generative models are deep neural network-based models trained to learn the underlying distribution of a dataset. Once trained, these models can be used to sample novel data points from this distribution. Their impressive capabilities have been manifested in various generative tasks, encompassing areas like image-to-image translation, style transfer, image editing, and more. One notable application of generative models is data augmentation, aimed at expanding and diversifying the training dataset to augment the performance of deep learning models for a downstream task. Generative models can be used to create new samples similar to the original data but with different variations and properties that are difficult to capture with traditional data augmentation techniques. However, the quality, diversity, and controllability of the shape and structure of the generated samples from these models are often directly proportional to the size and diversity of the training dataset. A more extensive and diverse training dataset allows the generative model to capture overall structures present in the data and generate more diverse and realistic-looking samples.
In this dissertation, I present innovative methods designed to enhance the robustness and controllability of generative models, drawing upon physics-based, probabilistic, and geometric techniques. These methods help improve the generalization and controllability of the generative model without necessarily relying on large training datasets. I enhance the robustness of generative models by integrating classical geometric moments for shape awareness and minimizing trainable parameters. Additionally, I employ non-parametric priors for the generative model's latent space through basic probability and optimization methods to improve the fidelity of interpolated images. I adopt a hybrid approach to address domain-specific challenges with limited data and controllability, combining physics-based rendering with generative models for more realistic results.
These approaches are particularly relevant in industrial settings, where the training datasets are small and class imbalance is common. Through extensive experiments on various datasets, I demonstrate the effectiveness of the proposed methods over conventional approaches.
ContributorsSingh, Rajhans (Author) / Turaga, Pavan (Thesis advisor) / Jayasuriya, Suren (Committee member) / Berisha, Visar (Committee member) / Fazli, Pooyan (Committee member) / Arizona State University (Publisher)
Created2023
Description
This dissertation presents novel solutions for improving the generalization capabilities of deep learning based computer vision models. Neural networks are known to suffer a large drop in performance when tested on samples from a different distribution than the one on which they were trained. The proposed solutions, based on latent space geometry and meta-learning, address this issue by improving the robustness of these models to distribution shifts. Through the use of geometrical alignment, state-of-the-art domain adaptation and source-free test-time adaptation strategies are developed. Additionally, geometrical alignment can allow classifiers to be progressively adapted to new, unseen test domains without requiring retraining of the feature extractors. The dissertation also presents algorithms for enabling in-the-wild generalization without needing access to any samples from the target domain. Other causes of poor generalization, such as data scarcity in critical applications and training data with high levels of noise and variance, are also explored. To address data scarcity in fine-grained computer vision tasks such as object detection, novel context-aware augmentations are suggested. While the first four chapters focus on general-purpose computer vision models, strategies are also developed to improve robustness in specific applications. The efficiency of training autonomous agents for visual navigation is improved by incorporating semantic knowledge, and the integration of domain experts' knowledge allows for the realization of a low-cost, minimally invasive generalizable automated rehabilitation system. Lastly, new tools for explainability and model introspection using counter-factual explainers trained through interval-based uncertainty calibration objectives are presented.
ContributorsThopalli, Kowshik (Author) / Turaga, Pavan (Thesis advisor) / Thiagarajan, Jayaraman J (Committee member) / Li, Baoxin (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2023
Description
The past decade witnessed the success of deep learning models in various applications of computer vision and natural language processing. This success can be predominantly attributed to the (i) availability of large amounts of training data; (ii) access of domain aware knowledge; (iii) i.i.d assumption between the train and target distributions and (iv) belief on existing metrics as reliable indicators of performance. When any of these assumptions are violated, the models exhibit brittleness producing adversely varied behavior. This dissertation focuses on methods for accurate model design and characterization that enhance process reliability when certain assumptions are not met. With the need to safely adopt artificial intelligence tools in practice, it is vital to build reliable failure detectors that indicate regimes where the model must not be invoked. To that end, an error predictor trained with a self-calibration objective is developed to estimate loss consistent with the underlying model. The properties of the error predictor are described and their utility in supporting introspection via feature importances and counterfactual explanations is elucidated. While such an approach can signal data regime changes, it is critical to calibrate models using regimes of inlier (training) and outlier data to prevent under- and over-generalization in models i.e., incorrectly identifying inliers as outliers and vice-versa. By identifying the space for specifying inliers and outliers, an anomaly detector that can effectively flag data of varying semantic complexities in medical imaging is next developed. Uncertainty quantification in deep learning models involves identifying sources of failure and characterizing model confidence to enable actionability. A training strategy is developed that allows the accurate estimation of model uncertainties and its benefits are demonstrated for active learning and generalization gap prediction. This helps identify insufficiently sampled regimes and representation insufficiency in models. In addition, the task of deep inversion under data scarce scenarios is considered, which in practice requires a prior to control the optimization. By identifying limitations in existing work, data priors powered by generative models and deep model priors are designed for audio restoration. With relevant empirical studies on a variety of benchmarks, the need for such design strategies is demonstrated.
ContributorsNarayanaswamy, Vivek Sivaraman (Author) / Spanias, Andreas (Thesis advisor) / J. Thiagarajan, Jayaraman (Committee member) / Berisha, Visar (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Arizona State University (Publisher)
Created2023
Description
Millimeter-wave (mmWave) and sub-terahertz (sub-THz) systems aim to utilize the large bandwidth available at these frequencies. This has the potential to enable several future applications that require high data rates, such as autonomous vehicles and digital twins. These systems, however, have several challenges that need to be addressed to realize their gains in practice. First, they need to deploy large antenna arrays and use narrow beams to guarantee sufficient receive power. Adjusting the narrow beams of the large antenna arrays incurs massive beam training overhead. Second, the sensitivity to blockages is a key challenge for mmWave and THz networks. Since these networks mainly rely on line-of-sight (LOS) links, sudden link blockages highly threaten the reliability of the networks. Further, when the LOS link is blocked, the network typically needs to hand off the user to another LOS basestation, which may incur critical time latency, especially if a search over a large codebook of narrow beams is needed. A promising way to tackle both these challenges lies in leveraging additional side information such as visual, LiDAR, radar, and position data. These sensors provide rich information about the wireless environment, which can be utilized for fast beam and blockage prediction. This dissertation presents a machine-learning framework for sensing-aided beam and blockage prediction. In particular, for beam prediction, this work proposes to utilize visual and positional data to predict the optimal beam indices. For the first time, this work investigates the sensing-aided beam prediction task in a real-world vehicle-to-infrastructure and drone communication scenario. Similarly, for blockage prediction, this dissertation proposes a multi-modal wireless communication solution that utilizes bimodal machine learning to perform proactive blockage prediction and user hand-off. Evaluations on both real-world and synthetic datasets illustrate the promising performance of the proposed solutions and highlight their potential for next-generation communication and sensing systems.
ContributorsCharan, Gouranga (Author) / Alkhateeb, Ahmed (Thesis advisor) / Chakrabarti, Chaitali (Committee member) / Turaga, Pavan (Committee member) / Michelusi, Nicolò (Committee member) / Arizona State University (Publisher)
Created2024
Description
Mixture of experts is a machine learning ensemble approach that consists of individual models that are trained to be ``experts'' on subsets of the data, and a gating network that provides weights to output a combination of the expert predictions. Mixture of experts models do not currently see wide use due to difficulty in training diverse experts and high computational requirements. This work presents modifications of the mixture of experts formulation that use domain knowledge to improve training, and incorporate parameter sharing among experts to reduce computational requirements.
First, this work presents an application of mixture of experts models for quality robust visual recognition. First it is shown that human subjects outperform deep neural networks on classification of distorted images, and then propose a model, MixQualNet, that is more robust to distortions. The proposed model consists of ``experts'' that are trained on a particular type of image distortion. The final output of the model is a weighted sum of the expert models, where the weights are determined by a separate gating network. The proposed model also incorporates weight sharing to reduce the number of parameters, as well as increase performance.
Second, an application of mixture of experts to predict visual saliency is presented. A computational saliency model attempts to predict where humans will look in an image. In the proposed model, each expert network is trained to predict saliency for a set of closely related images. The final saliency map is computed as a weighted mixture of the expert networks' outputs, with weights determined by a separate gating network. The proposed model achieves better performance than several other visual saliency models and a baseline non-mixture model.
Finally, this work introduces a saliency model that is a weighted mixture of models trained for different levels of saliency. Levels of saliency include high saliency, which corresponds to regions where almost all subjects look, and low saliency, which corresponds to regions where some, but not all subjects look. The weighted mixture shows improved performance compared with baseline models because of the diversity of the individual model predictions.
First, this work presents an application of mixture of experts models for quality robust visual recognition. First it is shown that human subjects outperform deep neural networks on classification of distorted images, and then propose a model, MixQualNet, that is more robust to distortions. The proposed model consists of ``experts'' that are trained on a particular type of image distortion. The final output of the model is a weighted sum of the expert models, where the weights are determined by a separate gating network. The proposed model also incorporates weight sharing to reduce the number of parameters, as well as increase performance.
Second, an application of mixture of experts to predict visual saliency is presented. A computational saliency model attempts to predict where humans will look in an image. In the proposed model, each expert network is trained to predict saliency for a set of closely related images. The final saliency map is computed as a weighted mixture of the expert networks' outputs, with weights determined by a separate gating network. The proposed model achieves better performance than several other visual saliency models and a baseline non-mixture model.
Finally, this work introduces a saliency model that is a weighted mixture of models trained for different levels of saliency. Levels of saliency include high saliency, which corresponds to regions where almost all subjects look, and low saliency, which corresponds to regions where some, but not all subjects look. The weighted mixture shows improved performance compared with baseline models because of the diversity of the individual model predictions.
ContributorsDodge, Samuel Fuller (Author) / Karam, Lina (Thesis advisor) / Jayasuriya, Suren (Committee member) / Li, Baoxin (Committee member) / Turaga, Pavan (Committee member) / Arizona State University (Publisher)
Created2018
Description
Several music players have evolved in multi-dimensional and surround sound systems. The audio players are implemented as software applications for different audio hardware systems. Digital formats and wireless networks allow for audio content to be readily accessible on smart networked devices. Therefore, different audio output platforms ranging from multispeaker high-end surround systems to single unit Bluetooth speakers have been developed. A large body of research has been carried out in audio processing, beamforming, sound fields etc. and new formats are developed to create realistic audio experiences.
An emerging trend is seen towards high definition AV systems, virtual reality gears as well as gaming applications with multidimensional audio. Next generation media technology is concentrating around Virtual reality experience and devices. It has applications not only in gaming but all other fields including medical, entertainment, engineering, and education. All such systems also require realistic audio corresponding with the visuals.
In the project presented in this thesis, a new portable audio hardware system is designed and developed along with a dedicated mobile android application to render immersive surround sound experiences with real-time audio effects. The tablet and mobile phone allow the user to control or “play” with sound directionality and implement various audio effects including sound rotation, spatialization, and other immersive experiences. The thesis describes the hardware and software design, provides the theory of the sound effects, and presents demonstrations of the sound application that was created.
An emerging trend is seen towards high definition AV systems, virtual reality gears as well as gaming applications with multidimensional audio. Next generation media technology is concentrating around Virtual reality experience and devices. It has applications not only in gaming but all other fields including medical, entertainment, engineering, and education. All such systems also require realistic audio corresponding with the visuals.
In the project presented in this thesis, a new portable audio hardware system is designed and developed along with a dedicated mobile android application to render immersive surround sound experiences with real-time audio effects. The tablet and mobile phone allow the user to control or “play” with sound directionality and implement various audio effects including sound rotation, spatialization, and other immersive experiences. The thesis describes the hardware and software design, provides the theory of the sound effects, and presents demonstrations of the sound application that was created.
ContributorsDharmadhikari, Chinmay (Author) / Spanias, Andreas (Thesis advisor) / Turaga, Pavan (Committee member) / Ingalls, Todd (Committee member) / Arizona State University (Publisher)
Created2016
Description
Head movement is known to have the benefit of improving the accuracy of sound localization for humans and animals. Marmoset is a small bodied New World monkey species and it has become an emerging model for studying the auditory functions. This thesis aims to detect the horizontal and vertical rotation of head movement in marmoset monkeys.
Experiments were conducted in a sound-attenuated acoustic chamber. Head movement of marmoset monkey was studied under various auditory and visual stimulation conditions. With increasing complexity, these conditions are (1) idle, (2) sound-alone, (3) sound and visual signals, and (4) alert signal by opening and closing of the chamber door. All of these conditions were tested with either house light on or off. Infra-red camera with a frame rate of 90 Hz was used to capture of the head movement of monkeys. To assist the signal detection, two circular markers were attached to the top of monkey head. The data analysis used an image-based marker detection scheme. Images were processed using the Computation Vision Toolbox in Matlab. The markers and their positions were detected using blob detection techniques. Based on the frame-by-frame information of marker positions, the angular position, velocity and acceleration were extracted in horizontal and vertical planes. Adaptive Otsu Thresholding, Kalman filtering and bound setting for marker properties were used to overcome a number of challenges encountered during this analysis, such as finding image segmentation threshold, continuously tracking markers during large head movement, and false alarm detection.
The results show that the blob detection method together with Kalman filtering yielded better performances than other image based techniques like optical flow and SURF features .The median of the maximal head turn in the horizontal plane was in the range of 20 to 70 degrees and the median of the maximal velocity in horizontal plane was in the range of a few hundreds of degrees per second. In comparison, the natural alert signal - door opening and closing - evoked the faster head turns than other stimulus conditions. These results suggest that behaviorally relevant stimulus such as alert signals evoke faster head-turn responses in marmoset monkeys.
Experiments were conducted in a sound-attenuated acoustic chamber. Head movement of marmoset monkey was studied under various auditory and visual stimulation conditions. With increasing complexity, these conditions are (1) idle, (2) sound-alone, (3) sound and visual signals, and (4) alert signal by opening and closing of the chamber door. All of these conditions were tested with either house light on or off. Infra-red camera with a frame rate of 90 Hz was used to capture of the head movement of monkeys. To assist the signal detection, two circular markers were attached to the top of monkey head. The data analysis used an image-based marker detection scheme. Images were processed using the Computation Vision Toolbox in Matlab. The markers and their positions were detected using blob detection techniques. Based on the frame-by-frame information of marker positions, the angular position, velocity and acceleration were extracted in horizontal and vertical planes. Adaptive Otsu Thresholding, Kalman filtering and bound setting for marker properties were used to overcome a number of challenges encountered during this analysis, such as finding image segmentation threshold, continuously tracking markers during large head movement, and false alarm detection.
The results show that the blob detection method together with Kalman filtering yielded better performances than other image based techniques like optical flow and SURF features .The median of the maximal head turn in the horizontal plane was in the range of 20 to 70 degrees and the median of the maximal velocity in horizontal plane was in the range of a few hundreds of degrees per second. In comparison, the natural alert signal - door opening and closing - evoked the faster head turns than other stimulus conditions. These results suggest that behaviorally relevant stimulus such as alert signals evoke faster head-turn responses in marmoset monkeys.
ContributorsSimhadri, Sravanthi (Author) / Zhou, Yi (Thesis advisor) / Turaga, Pavan (Thesis advisor) / Berisha, Visar (Committee member) / Arizona State University (Publisher)
Created2014
Description
The performance of most of the visual computing tasks depends on the quality of the features extracted from the raw data. Insightful feature representation increases the performance of many learning algorithms by exposing the underlying explanatory factors of the output for the unobserved input. A good representation should also handle anomalies in the data such as missing samples and noisy input caused by the undesired, external factors of variation. It should also reduce the data redundancy. Over the years, many feature extraction processes have been invented to produce good representations of raw images and videos.
The feature extraction processes can be categorized into three groups. The first group contains processes that are hand-crafted for a specific task. Hand-engineering features requires the knowledge of domain experts and manual labor. However, the feature extraction process is interpretable and explainable. Next group contains the latent-feature extraction processes. While the original feature lies in a high-dimensional space, the relevant factors for a task often lie on a lower dimensional manifold. The latent-feature extraction employs hidden variables to expose the underlying data properties that cannot be directly measured from the input. Latent features seek a specific structure such as sparsity or low-rank into the derived representation through sophisticated optimization techniques. The last category is that of deep features. These are obtained by passing raw input data with minimal pre-processing through a deep network. Its parameters are computed by iteratively minimizing a task-based loss.
In this dissertation, I present four pieces of work where I create and learn suitable data representations. The first task employs hand-crafted features to perform clinically-relevant retrieval of diabetic retinopathy images. The second task uses latent features to perform content-adaptive image enhancement. The third task ranks a pair of images based on their aestheticism. The goal of the last task is to capture localized image artifacts in small datasets with patch-level labels. For both these tasks, I propose novel deep architectures and show significant improvement over the previous state-of-art approaches. A suitable combination of feature representations augmented with an appropriate learning approach can increase performance for most visual computing tasks.
The feature extraction processes can be categorized into three groups. The first group contains processes that are hand-crafted for a specific task. Hand-engineering features requires the knowledge of domain experts and manual labor. However, the feature extraction process is interpretable and explainable. Next group contains the latent-feature extraction processes. While the original feature lies in a high-dimensional space, the relevant factors for a task often lie on a lower dimensional manifold. The latent-feature extraction employs hidden variables to expose the underlying data properties that cannot be directly measured from the input. Latent features seek a specific structure such as sparsity or low-rank into the derived representation through sophisticated optimization techniques. The last category is that of deep features. These are obtained by passing raw input data with minimal pre-processing through a deep network. Its parameters are computed by iteratively minimizing a task-based loss.
In this dissertation, I present four pieces of work where I create and learn suitable data representations. The first task employs hand-crafted features to perform clinically-relevant retrieval of diabetic retinopathy images. The second task uses latent features to perform content-adaptive image enhancement. The third task ranks a pair of images based on their aestheticism. The goal of the last task is to capture localized image artifacts in small datasets with patch-level labels. For both these tasks, I propose novel deep architectures and show significant improvement over the previous state-of-art approaches. A suitable combination of feature representations augmented with an appropriate learning approach can increase performance for most visual computing tasks.
ContributorsChandakkar, Parag Shridhar (Author) / Li, Baoxin (Thesis advisor) / Yang, Yezhou (Committee member) / Turaga, Pavan (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2017