Filtering by
- All Subjects: Computer Science
The expression and perception of emotions varies across speakers and cultures, thus, determining features and classification methods that generalize well to different conditions is strongly desired. A latent topic models-based method is proposed to learn supra-segmental features from low-level acoustic descriptors. The derived features outperform state-of-the-art approaches over multiple databases. Cross-corpus studies are conducted to determine the ability of these features to generalize well across different databases. The proposed method is also applied to derive features from facial expressions; a multi-modal fusion overcomes the deficiencies of a speech only approach and further improves the recognition performance.
Besides affecting the acoustic properties of speech, emotions have a strong influence over speech articulation kinematics. A learning approach, which constrains a classifier trained over acoustic descriptors, to also model articulatory data is proposed here. This method requires articulatory information only during the training stage, thus overcoming the challenges inherent to large-scale data collection, while simultaneously exploiting the correlations between articulation kinematics and acoustic descriptors to improve the accuracy of emotion recognition systems.
Identifying context from ambient sounds in a lifelogging scenario requires feature extraction, segmentation and annotation techniques capable of efficiently handling long duration audio recordings; a complete framework for such applications is presented. The performance is evaluated on real world data and accompanied by a prototypical Android-based user interface.
The proposed methods are also assessed in terms of computation and implementation complexity. Software and field programmable gate array based implementations are considered for emotion recognition, while virtual platforms are used to model the complexities of lifelogging. The derived metrics are used to determine the feasibility of these methods for applications requiring real-time capabilities and low power consumption.
We first consider sensor fusion, a typical multimodal fusion problem critical to building a pervasive computing platform. A systematic fusion technique is described to support both multiple sensors and descriptors for activity recognition. Targeted to learn the optimal combination of kernels, Multiple Kernel Learning (MKL) algorithms have been successfully applied to numerous fusion problems in computer vision etc. Utilizing the MKL formulation, next we describe an auto-context algorithm for learning image context via the fusion with low-level descriptors. Furthermore, a principled fusion algorithm using deep learning to optimize kernel machines is developed. By bridging deep architectures with kernel optimization, this approach leverages the benefits of both paradigms and is applied to a wide variety of fusion problems.
In many real-world applications, the modalities exhibit highly specific data structures, such as time sequences and graphs, and consequently, special design of the learning architecture is needed. In order to improve the temporal modeling for multivariate sequences, we developed two architectures centered around attention models. A novel clinical time series analysis model is proposed for several critical problems in healthcare. Another model coupled with triplet ranking loss as metric learning framework is described to better solve speaker diarization. Compared to state-of-the-art recurrent networks, these attention-based multivariate analysis tools achieve improved performance while having a lower computational complexity. Finally, in order to perform community detection on multilayer graphs, a fusion algorithm is described to derive node embedding from word embedding techniques and also exploit the complementary relational information contained in each layer of the graph.
To overcome these challenges, recent works have extensively investigated model compression techniques such as element-wise sparsity, structured sparsity and quantization. While most of these works have applied these compression techniques in isolation, there have been very few studies on application of quantization and structured sparsity together on a DNN model.
This thesis co-optimizes structured sparsity and quantization constraints on DNN models during training. Specifically, it obtains optimal setting of 2-bit weight and 2-bit activation coupled with 4X structured compression by performing combined exploration of quantization and structured compression settings. The optimal DNN model achieves 50X weight memory reduction compared to floating-point uncompressed DNN. This memory saving is significant since applying only structured sparsity constraints achieves 2X memory savings and only quantization constraints achieves 16X memory savings. The algorithm has been validated on both high and low capacity DNNs and on wide-sparse and deep-sparse DNN models. Experiments demonstrated that deep-sparse DNN outperforms shallow-dense DNN with varying level of memory savings depending on DNN precision and sparsity levels. This work further proposed a Pareto-optimal approach to systematically extract optimal DNN models from a huge set of sparse and dense DNN models. The resulting 11 optimal designs were further evaluated by considering overall DNN memory which includes activation memory and weight memory. It was found that there is only a small change in the memory footprint of the optimal designs corresponding to the low sparsity DNNs. However, activation memory cannot be ignored for high sparsity DNNs.
This dissertation focuses on how dialogue systems can build rapport utilizing acoustic-prosodic entrainment. Acoustic-prosodic entrainment occurs when individuals adapt their acoustic-prosodic features of speech, such as tone of voice or loudness, to one another over the course of a conversation. Correlated with liking and task success, a dialogue system which entrains may enhance rapport. Entrainment, however, is very challenging to model. People entrain on different features in many ways and how to design entrainment to build rapport is unclear. The first goal of this dissertation is to explore how acoustic-prosodic entrainment can be modeled to build rapport.
Towards this goal, this work presents a series of studies comparing, evaluating, and iterating on the design of entrainment, motivated and informed by human-human dialogue. These models of entrainment are implemented in the dialogue system of a robotic learning companion. Learning companions are educational agents that engage students socially to increase motivation and facilitate learning. As a learning companion’s ability to be socially responsive increases, so do vital learning outcomes. A second goal of this dissertation is to explore the effects of entrainment on concrete outcomes such as learning in interactions with robotic learning companions.
This dissertation results in contributions both technical and theoretical. Technical contributions include a robust and modular dialogue system capable of producing prosodic entrainment and other socially-responsive behavior. One of the first systems of its kind, the results demonstrate that an entraining, social learning companion can positively build rapport and increase learning. This dissertation provides support for exploring phenomena like entrainment to enhance factors such as rapport and learning and provides a platform with which to explore these phenomena in future work.
The purpose of this study is to know whether the primary motor cortex (M1) plays a role in the sensorimotor memory. It was hypothesized that temporary disruption of the M1 following the learning to minimize a tilt using a ‘L’ shaped object would negatively affect the retention of sensorimotor memory and thus reduce interference between the memory acquired in one context and the visual cues to perform the same task in a different context.
Significant findings were shown in blocks 1, 2, and 4. In block 3, subjects displayed insignificant amount of learning. However, it cannot be concluded that there is full interference in block 3. Therefore, looked into 3 effects in statistical analysis: the main effects of the blocks, the main effects of the trials, and the effects of the blocks and trials combined. From the block effects, there is a p-value of 0.001, and from the trial effects, the p-value is less than 0.001. Both of these effects indicate that there is learning occurring. However, when looking at the blocks * trials effects, we see a p-value of 0.002 < 0.05 indicating significant interaction between sensorimotor memories. Based on the results that were found, there is a presence of interference in all the blocks but not enough to justify the use of TMS in order to reduce interference because there is a partial reduction of interference from the control experiment. It is evident that the time delay might be the issue between context switches. By reducing the time delay between block 2 and 3 from 10 minutes to 5 minutes, I will hope to see significant learning to occur from the first trial to the second trial.
Spatial audio can be especially useful for directing human attention. However, delivering spatial audio through speakers, rather than headphones that deliver audio directly to the ears, produces the issue of crosstalk, where sounds from each of the two speakers reach the opposite ear, inhibiting the spatialized effect. A research team at Meteor Studio has developed an algorithm called Xblock that solves this issue using a crosstalk cancellation technique. This thesis project expands upon the existing Xblock IoT system by providing a way to test the accuracy of the directionality of sounds generated with spatial audio. More specifically, the objective is to determine whether the usage of Xblock with smart speakers can provide generalized audio localization, which refers to the ability to detect a general direction of where a sound might be coming from. This project also expands upon the existing Xblock technique to integrate voice commands, where users can verbalize the name of a lost item using the phrase, “Find [item]”, and the IoT system will use spatial audio to guide them to it.