It is challenging to extract semantic meanings directly from audio signals in spoken language understanding (SLU), due to the lack of textual information. Popular end-to-end (E2E) SLU models utilize sequence-to-sequence automatic speech recognition (ASR) models to extract textual embeddings as input to infer semantics, which, however, require computationally expensive auto-regressive decoding. In this work, we leverage self-supervised acoustic encoders fine-tuned with Connectionist Temporal Classification (CTC) to extract textual embeddings and use joint CTC and SLU losses for utterance-level SLU tasks. Experiments show that our model achieves 4% absolute improvement over the the state-of-the-art (SOTA) dialogue act classification model on the DSTC2 dataset and 1.3% absolute improvement over the SOTA SLU model on the SLURP dataset.
In order to advance underwater computer vision and robotics from lab environments and clear water scenarios to the deep dark ocean or murky coastal waters, representative benchmarks and realistic datasets with ground truth information are required. In particular, determining the camera pose is essential for many underwater robotic or photogrammetric applications and known ground truth is mandatory to evaluate the performance of e.g., simultaneous localization and mapping approaches in such extreme environments. This paper presents the conception, calibration and implementation of an external reference system for determining the underwater camera pose in real-time. The approach, based on an HTC Vive tracking system in air, calculates the underwater camera pose by fusing the poses of two controllers tracked above the water surface of a tank. It is shown that the mean deviation of this approach to an optical marker based reference in air is less than 3 mm and 0.3{\deg}. Finally, the usability of the system for underwater applications is demonstrated.
In recent years, there is an increasing interests in reconstruction based generative models for image One-Class Novelty Detection, most of which only focus on image-level information. While in this paper, we further exploit the latent space of Variational Auto-encoder (VAE), a typical reconstruction based model, and we innovatively divide it into three regions: Normal/Anomalous/Unknown-semantic-region. Based on this hypothesis, we propose a new VAE architecture, Recoding Semantic Consistency Based VAE (RSC-VAE), combining VAE with recoding mechanism and constraining the semantic consistency of two encodings. We come up with three training modes of RSC-VAE: 1. One-Class Training Mode, alleviating False Positive problem of normal samples; 2. Distributionally-Shifted Training Mode, alleviating False Negative problem of anomalous samples; 3. Extremely-Imbalanced Training Mode, introducing a small number of anomalous samples for training to enhance the second mode. The experimental results on multiple datasets demonstrate that our mechanism achieves state-of-the-art performance in various baselines including VAE.
As a prerequisite of chart data extraction, the accurate detection of chart basic elements is essential and mandatory. In contrast to object detection in the general image domain, chart element detection relies heavily on context information as charts are highly structured data visualization formats. To address this, we propose a novel method CACHED, which stands for Context-Aware Chart Element Detection, by integrating a local-global context fusion module consisting of visual context enhancement and positional context encoding with the Cascade R-CNN framework. To improve the generalization of our method for broader applicability, we refine the existing chart element categorization and standardized 18 classes for chart basic elements, excluding plot elements. Our CACHED method, with the updated category of chart elements, achieves state-of-the-art performance in our experiments, underscoring the importance of context in chart element detection. Extending our method to the bar plot detection task, we obtain the best result on the PMC test dataset.
Although procedural generation is popular among game developers, academic research on the topic has primarily focused on new applications, with some research into empirical analysis. In this paper we relate theoretical work in information theory to the generation of content for games. We prove that there is a relationship between the Kolomogorov complexity of the most complex artifact a generator can produce, and the size of that generator's possibility space. In doing so, we identify the limiting relationship between the knowledge encoded in a generator, the density of its output space, and the intricacy of the artifacts it produces. We relate our result to the experience of expert procedural generator designers, and illustrate it with some examples.
Data extraction from line-chart images is an essential component of the automated document understanding process, as line charts are a ubiquitous data visualization format. However, the amount of visual and structural variations in multi-line graphs makes them particularly challenging for automated parsing. Existing works, however, are not robust to all these variations, either taking an all-chart unified approach or relying on auxiliary information such as legends for line data extraction. In this work, we propose LineFormer, a robust approach to line data extraction using instance segmentation. We achieve state-of-the-art performance on several benchmark synthetic and real chart datasets. Our implementation is available at https://github.com/TheJaeLal/LineFormer .
Speech data carries a range of personal information, such as the speaker's identity and emotional state. These attributes can be used for malicious purposes. With the development of virtual assistants, a new generation of privacy threats has emerged. Current studies have addressed the topic of preserving speech privacy. One of them, the VoicePrivacy initiative aims to promote the development of privacy preservation tools for speech technology. The task selected for the VoicePrivacy 2020 Challenge (VPC) is about speaker anonymization. The goal is to hide the source speaker's identity while preserving the linguistic information. The baseline of the VPC makes use of a voice conversion. This paper studies the impact of the speaker anonymization baseline system of the VPC on emotional information present in speech utterances. Evaluation is performed following the VPC rules regarding the attackers' knowledge about the anonymization system. Our results show that the VPC baseline system does not suppress speakers' emotions against informed attackers. When comparing anonymized speech to original speech, the emotion recognition performance is degraded by 15\% relative to IEMOCAP data, similar to the degradation observed for automatic speech recognition used to evaluate the preservation of the linguistic information.
In the era of big data, there is an increasing need for healthcare providers, communities, and researchers to share data and collaborate to improve health outcomes, generate valuable insights, and advance research. The Health Insurance Portability and Accountability Act of 1996 (HIPAA) is a federal law designed to protect sensitive health information by defining regulations for protected health information (PHI). However, it does not provide efficient tools for detecting or removing PHI before data sharing. One of the challenges in this area of research is the heterogeneous nature of PHI fields in data across different parties. This variability makes rule-based sensitive variable identification systems that work on one database fail on another. To address this issue, our paper explores the use of machine learning algorithms to identify sensitive variables in structured data, thus facilitating the de-identification process. We made a key observation that the distributions of metadata of PHI fields and non-PHI fields are very different. Based on this novel finding, we engineered over 30 features from the metadata of the original features and used machine learning to build classification models to automatically identify PHI fields in structured Electronic Health Record (EHR) data. We trained the model on a variety of large EHR databases from different data sources and found that our algorithm achieves 99% accuracy when detecting PHI-related fields for unseen datasets. The implications of our study are significant and can benefit industries that handle sensitive data.
The measure of a machine learning algorithm is the difficulty of the tasks it can perform, and sufficiently difficult tasks are critical drivers of strong machine learning models. However, quantifying the generalization difficulty of machine learning benchmarks has remained challenging. We propose what is to our knowledge the first model-agnostic measure of the inherent generalization difficulty of tasks. Our inductive bias complexity measure quantifies the total information required to generalize well on a task minus the information provided by the data. It does so by measuring the fractional volume occupied by hypotheses that generalize on a task given that they fit the training data. It scales exponentially with the intrinsic dimensionality of the space over which the model must generalize but only polynomially in resolution per dimension, showing that tasks which require generalizing over many dimensions are drastically more difficult than tasks involving more detail in fewer dimensions. Our measure can be applied to compute and compare supervised learning, reinforcement learning and meta-learning generalization difficulties against each other. We show that applied empirically, it formally quantifies intuitively expected trends, e.g. that in terms of required inductive bias, MNIST < CIFAR10 < Imagenet and fully observable Markov decision processes (MDPs) < partially observable MDPs. Further, we show that classification of complex images $<$ few-shot meta-learning with simple images. Our measure provides a quantitative metric to guide the construction of more complex tasks requiring greater inductive bias, and thereby encourages the development of more sophisticated architectures and learning algorithms with more powerful generalization capabilities.
There has been significant progress in generating an animatable 3D human avatar from a single image. However, recovering texture for the 3D human avatar from a single image has been relatively less addressed. Because the generated 3D human avatar reveals the occluded texture of the given image as it moves, it is critical to synthesize the occluded texture pattern that is unseen from the source image. To generate a plausible texture map for 3D human avatars, the occluded texture pattern needs to be synthesized with respect to the visible texture from the given image. Moreover, the generated texture should align with the surface of the target 3D mesh. In this paper, we propose a texture synthesis method for a 3D human avatar that incorporates geometry information. The proposed method consists of two convolutional networks for the sampling and refining process. The sampler network fills in the occluded regions of the source image and aligns the texture with the surface of the target 3D mesh using the geometry information. The sampled texture is further refined and adjusted by the refiner network. To maintain the clear details in the given image, both sampled and refined texture is blended to produce the final texture map. To effectively guide the sampler network to achieve its goal, we designed a curriculum learning scheme that starts from a simple sampling task and gradually progresses to the task where the alignment needs to be considered. We conducted experiments to show that our method outperforms previous methods qualitatively and quantitatively.