Spatial sound reasoning is a fundamental human skill, enabling us to navigate and interpret our surroundings based on sound. In this paper we present BAT, which combines the spatial sound perception ability of a binaural acoustic scene analysis model with the natural language reasoning capabilities of a large language model (LLM) to replicate this innate ability. To address the lack of existing datasets of in-the-wild spatial sounds, we synthesized a binaural audio dataset using AudioSet and SoundSpaces 2.0. Next, we developed SpatialSoundQA, a spatial sound-based question-answering dataset, offering a range of QA tasks that train BAT in various aspects of spatial sound perception and reasoning. The acoustic front end encoder of BAT is a novel spatial audio encoder named Spatial Audio Spectrogram Transformer, or Spatial-AST, which by itself achieves strong performance across sound event detection, spatial localization, and distance estimation. By integrating Spatial-AST with LLaMA-2 7B model, BAT transcends standard Sound Event Localization and Detection (SELD) tasks, enabling the model to reason about the relationships between the sounds in its environment. Our experiments demonstrate BAT's superior performance on both spatial sound perception and reasoning, showcasing the immense potential of LLMs in navigating and interpreting complex spatial audio environments.
Rapid identification and response to breaking events, particularly those that pose a threat to human life such as natural disasters or conflicts, is of paramount importance. The prevalence of mobile devices and the ubiquity of network connectivity has generated a massive amount of temporally- and spatially-stamped data. Numerous studies have used mobile data to derive individual human mobility patterns for various applications. Similarly, the increasing number of orbital satellites has made it easier to gather high-resolution images capturing a snapshot of a geographical area in sub-daily temporal frequency. We propose a novel data fusion methodology integrating satellite imagery with privacy-enhanced mobile data to augment the event inference task, whether in real-time or historical. In the absence of boots on the ground, mobile data is able to give an approximation of human mobility, proximity to one another, and the built environment. On the other hand, satellite imagery can provide visual information on physical changes to the built and natural environment. The expected use cases for our methodology include small-scale disaster detection (i.e., tornadoes, wildfires, and floods) in rural regions, search and rescue operation augmentation for lost hikers in remote wilderness areas, and identification of active conflict areas and population displacement in war-torn states. Our implementation is open-source on GitHub: https://github.com/ekinugurel/SatMobFusion.
Transfer learning (TL) is an increasingly popular approach to training deep learning (DL) models that leverages the knowledge gained by training a foundation model on diverse, large-scale datasets for use on downstream tasks where less domain- or task-specific data is available. The literature is rich with TL techniques and applications; however, the bulk of the research makes use of deterministic DL models which are often uncalibrated and lack the ability to communicate a measure of epistemic (model) uncertainty in prediction. Unlike their deterministic counterparts, Bayesian DL (BDL) models are often well-calibrated, provide access to epistemic uncertainty for a prediction, and are capable of achieving competitive predictive performance. In this study, we propose variational inference pre-trained audio neural networks (VI-PANNs). VI-PANNs are a variational inference variant of the popular ResNet-54 architecture which are pre-trained on AudioSet, a large-scale audio event detection dataset. We evaluate the quality of the resulting uncertainty when transferring knowledge from VI-PANNs to other downstream acoustic classification tasks using the ESC-50, UrbanSound8K, and DCASE2013 datasets. We demonstrate, for the first time, that it is possible to transfer calibrated uncertainty information along with knowledge from upstream tasks to enhance a model's capability to perform downstream tasks.
Recently, 2D convolution has been found unqualified in sound event detection (SED). It enforces translation equivariance on sound events along frequency axis, which is not a shift-invariant dimension. To address this issue, dynamic convolution is used to model the frequency dependency of sound events. In this paper, we proposed the first full-dynamic method named full-frequency dynamic convolution (FFDConv). FFDConv generates frequency kernels for every frequency band, which is designed directly in the structure for frequency-dependent modeling. It physically furnished 2D convolution with the capability of frequency-dependent modeling. FFDConv outperforms not only the baseline by 6.6% in DESED real validation dataset in terms of PSDS1, but outperforms the other full-dynamic methods. In addition, by visualizing features of sound events, we observed that FFDConv could effectively extract coherent features in specific frequency bands, consistent with the vocal continuity of sound events. This proves that FFDConv has great frequency-dependent perception ability.
Transformers have achieved promising results on a variety of tasks. However, the quadratic complexity in self-attention computation has limited the applications, especially in low-resource settings and mobile or edge devices. Existing works have proposed to exploit hand-crafted attention patterns to reduce computation complexity. However, such hand-crafted patterns are data-agnostic and may not be optimal. Hence, it is likely that relevant keys or values are being reduced, while less important ones are still preserved. Based on this key insight, we propose a novel deformable audio Transformer for audio recognition, named DATAR, where a deformable attention equipping with a pyramid transformer backbone is constructed and learnable. Such an architecture has been proven effective in prediction tasks,~\textit{e.g.}, event classification. Moreover, we identify that the deformable attention map computation may over-simplify the input feature, which can be further enhanced. Hence, we introduce a learnable input adaptor to alleviate this issue, and DATAR achieves state-of-the-art performance.
As a trending approach for social event detection, graph neural network (GNN)-based methods enable a fusion of natural language semantics and the complex social network structural information, thus showing SOTA performance. However, GNN-based methods can miss useful message correlations. Moreover, they require manual labeling for training and predetermining the number of events for prediction. In this work, we address social event detection via graph structural entropy (SE) minimization. While keeping the merits of the GNN-based methods, the proposed framework, HISEvent, constructs more informative message graphs, is unsupervised, and does not require the number of events given a priori. Specifically, we incrementally explore the graph neighborhoods using 1-dimensional (1D) SE minimization to supplement the existing message graph with edges between semantically related messages. We then detect events from the message graph by hierarchically minimizing 2-dimensional (2D) SE. Our proposed 1D and 2D SE minimization algorithms are customized for social event detection and effectively tackle the efficiency problem of the existing SE minimization algorithms. Extensive experiments show that HISEvent consistently outperforms GNN-based methods and achieves the new SOTA for social event detection under both closed- and open-set settings while being efficient and robust.
Sound event localization and detection (SELD) combines two subtasks: sound event detection (SED) and direction of arrival (DOA) estimation. SELD is usually tackled as an audio-only problem, but visual information has been recently included. Few audio-visual (AV)-SELD works have been published and most employ vision via face/object bounding boxes, or human pose keypoints. In contrast, we explore the integration of audio and visual feature embeddings extracted with pre-trained deep networks. For the visual modality, we tested ResNet50 and Inflated 3D ConvNet (I3D). Our comparison of AV fusion methods includes the AV-Conformer and Cross-Modal Attentive Fusion (CMAF) model. Our best models outperform the DCASE 2023 Task3 audio-only and AV baselines by a wide margin on the development set of the STARSS23 dataset, making them competitive amongst state-of-the-art results of the AV challenge, without model ensembling, heavy data augmentation, or prediction post-processing. Such techniques and further pre-training could be applied as next steps to improve performance.
Detecting events from social media data streams is gradually attracting researchers. The innate challenge for detecting events is to extract discriminative information from social media data thereby assigning the data into different events. Due to the excessive diversity and high updating frequency of social data, using supervised approaches to detect events from social messages is hardly achieved. To this end, recent works explore learning discriminative information from social messages by leveraging graph contrastive learning (GCL) and embedding clustering in an unsupervised manner. However, two intrinsic issues exist in benchmark methods: conventional GCL can only roughly explore partial attributes, thereby insufficiently learning the discriminative information of social messages; for benchmark methods, the learned embeddings are clustered in the latent space by taking advantage of certain specific prior knowledge, which conflicts with the principle of unsupervised learning paradigm. In this paper, we propose a novel unsupervised social media event detection method via hybrid graph contrastive learning and reinforced incremental clustering (HCRC), which uses hybrid graph contrastive learning to comprehensively learn semantic and structural discriminative information from social messages and reinforced incremental clustering to perform efficient clustering in a solidly unsupervised manner. We conduct comprehensive experiments to evaluate HCRC on the Twitter and Maven datasets. The experimental results demonstrate that our approach yields consistent significant performance boosts. In traditional incremental setting, semi-supervised incremental setting and solidly unsupervised setting, the model performance has achieved maximum improvements of 53%, 45%, and 37%, respectively.
Sleep detection and annotation are crucial for researchers to understand sleep patterns, especially in children. With modern wrist-worn watches comprising built-in accelerometers, sleep logs can be collected. However, the annotation of these logs into distinct sleep events: onset and wakeup, proves to be challenging. These annotations must be automated, precise, and scalable. We propose to model the accelerometer data using different machine learning (ML) techniques such as support vectors, boosting, ensemble methods, and more complex approaches involving LSTMs and Region-based CNNs. Later, we aim to evaluate these approaches using the Event Detection Average Precision (EDAP) score (similar to the IOU metric) to eventually compare the predictive power and model performance.
Dynamic scene understanding is the ability of a computer system to interpret and make sense of the visual information present in a video of a real-world scene. In this thesis, we present a series of frameworks for dynamic scene understanding starting from road event detection from an autonomous driving perspective to complex video activity detection, followed by continual learning approaches for the life-long learning of the models. Firstly, we introduce the ROad event Awareness Dataset (ROAD) for Autonomous Driving, to our knowledge the first of its kind. Due to the lack of datasets equipped with formally specified logical requirements, we also introduce the ROad event Awareness Dataset with logical Requirements (ROAD-R), the first publicly available dataset for autonomous driving with requirements expressed as logical constraints, as a tool for driving neurosymbolic research in the area. Next, we extend event detection to holistic scene understanding by proposing two complex activity detection methods. In the first method, we present a deformable, spatiotemporal scene graph approach, consisting of three main building blocks: action tube detection, a 3D deformable RoI pooling layer designed for learning the flexible, deformable geometry of the constituent action tubes, and a scene graph constructed by considering all parts as nodes and connecting them based on different semantics. In a second approach evolving from the first, we propose a hybrid graph neural network that combines attention applied to a graph encoding of the local (short-term) dynamic scene with a temporal graph modelling the overall long-duration activity. Finally, the last part of the thesis is about presenting a new continual semi-supervised learning (CSSL) paradigm.
Sound Event Detection and Localization (SELD) constitutes a complex task that depends on extensive multichannel audio recordings with annotated sound events and their respective locations. In this paper, we introduce a self-supervised approach for SELD adapted from the pre-training methodology of wav2vec 2.0, which learns representations directly from raw audio data, eliminating the need for supervision. By applying this approach to SELD, we can leverage a substantial amount of unlabeled 3D audio data to learn robust representations of sound events and their locations. Our method comprises two primary stages: pre-training and fine-tuning. In the pre-training phase, unlabeled 3D audio datasets are utilized to train our w2v-SELD model, capturing intricate high-level features and contextual information inherent in audio signals. Subsequently, in the fine-tuning stage, a smaller dataset with labeled SELD data fine-tunes the pre-trained model. Experimental results on benchmark datasets demonstrate the effectiveness of the proposed self-supervised approach for SELD. The model surpasses baseline systems provided with the datasets and achieves competitive performance comparable to state-of-the-art supervised methods. The code and pre-trained parameters of our w2v-SELD model are available in this repository.
Event detection in time series is a challenging task due to the prevalence of imbalanced datasets, rare events, and time interval-defined events. Traditional supervised deep learning methods primarily employ binary classification, where each time step is assigned a binary label indicating the presence or absence of an event. However, these methods struggle to handle these specific scenarios effectively. To address these limitations, we propose a novel supervised regression-based deep learning approach that offers several advantages over classification-based methods. Our approach, with a limited number of parameters, can effectively handle various types of events within a unified framework, including rare events and imbalanced datasets. We provide theoretical justifications for its universality and precision and demonstrate its superior performance across diverse domains, particularly for rare events and imbalanced datasets.
Traditional binary hard labels for sound event detection (SED) lack details about the complexity and variability of sound event distributions. Recently, a novel annotation workflow is proposed to generate fine-grained non-binary soft labels, resulting in a new real-life dataset named MAESTRO Real for SED. In this paper, we first propose an interactive dual-conformer (IDC) module, in which a cross-interaction mechanism is applied to effectively exploit the information from soft labels. In addition, a novel scene-inspired mask (SIM) based on soft labels is incorporated for more precise SED predictions. The SIM is initially generated through a statistical approach, referred as SIM-V1. However, the fixed artificial mask may mismatch the SED model, resulting in limited effectiveness. Therefore, we further propose SIM-V2, which employs a word embedding model for adaptive SIM estimation. Experimental results show that the proposed IDC module can effectively utilize the information from soft labels, and the integration of SIM-V1 can further improve the accuracy. In addition, the impact of different word embedding dimensions on SIM-V2 is explored, and the results show that the appropriate dimension can enable SIM-V2 achieve superior performance than SIM-V1. In DCASE 2023 Challenge Task4B, the proposed system achieved the top ranking performance on the evaluation dataset of MAESTRO Real.
Since rumors widely spread on social networks can cause seri- ous negative impacts, a batch of studies have investigated how to detect rumors. Most of them rely on existing datasets and try to improve the detection performance on those known datasets, but their performance drops significantly when detecting newly emerging events. This is not in line with the original intention of the rumor detection task. To tackle this issue, we formulate the rumor detection problem as a domain adaption task and propose the Class-based Adversarial Domain Adaptive framework, CADA, which is a general model framework where any latest rumor detec- tion methods can be plugged-in. The improvement of new emerging rumor event detection is based on adversarial training. Specifically, CADA considers class-based discriminators to achieve fine-grained alignment of declarations to be detected of different classes. Ex- periments on three public datasets show that CADA can improve the detection performance of existing rumor detection models and achieve better results than state-of-the-art models. In terms of ac- curacy, the performance is improved by at least 3% compared with the original base model in the PHEME dataset, and as high as 10% in the Twitter datasets.
Contrastive Language-Audio Pretraining (CLAP) became of crucial importance in the field of audio and speech processing. Its employment ranges from sound event detection to text-to-audio generation. However, one of the main limitations is the considerable amount of data required in the training process and the overall computational complexity during inference. This paper investigates how we can reduce the complexity of contrastive language-audio pre-trained models, yielding an efficient model that we call tinyCLAP. We derive an unimodal distillation loss from first principles and explore how the dimensionality of the shared, multimodal latent space can be reduced via pruning. TinyCLAP uses only 6% of the original Microsoft CLAP parameters with a minimal reduction (less than 5%) in zero-shot classification performance across the three sound event detection datasets on which it was tested
Accounting for the increased concern for public safety, automatic abnormal event detection and recognition in a surveillance scene is crucial. It is a current open study subject because of its intricacy and utility. The identification of aberrant events automatically, it's a difficult undertaking because everyone's idea of abnormality is different. A typical occurrence in one circumstance could be seen as aberrant in another. Automatic anomaly identification becomes particularly challenging in the surveillance footage with a large crowd due to congestion and high occlusion. With the use of machine learning techniques, this thesis study aims to offer the solution for this use case so that human resources won't be required to keep an eye out for any unusual activity in the surveillance system records. We have developed a novel generative adversarial network (GAN) based anomaly detection model. This model is trained such that it learns together about constructing a high dimensional picture space and determining the latent space from the video's context. The generator uses a residual Autoencoder architecture made up of a multi-stage channel attention-based decoder and a two-stream, deep convolutional encoder that can realise both spatial and temporal data. We have also offered a technique for refining the GAN model that reduces training time while also generalising the model by utilising transfer learning between datasets. Using a variety of assessment measures, we compare our model to the current state-of-the-art techniques on four benchmark datasets. The empirical findings indicate that, in comparison to existing techniques, our network performs favourably on all datasets.
Previous studies in automated audio captioning have faced difficulties in accurately capturing the complete temporal details of acoustic scenes and events within long audio sequences. This paper presents AudioLog, a large language models (LLMs)-powered audio logging system with hybrid token-semantic contrastive learning. Specifically, we propose to fine-tune the pre-trained hierarchical token-semantic audio Transformer by incorporating contrastive learning between hybrid acoustic representations. We then leverage LLMs to generate audio logs that summarize textual descriptions of the acoustic environment. Finally, we evaluate the AudioLog system on two datasets with both scene and event annotations. Experiments show that the proposed system achieves exceptional performance in acoustic scene classification and sound event detection, surpassing existing methods in the field. Further analysis of the prompts to LLMs demonstrates that AudioLog can effectively summarize long audio sequences. To the best of our knowledge, this approach is the first attempt to leverage LLMs for summarizing long audio sequences.
Simulation is a prospective method for generating diverse and realistic traffic scenarios to aid in the development of driving decision-making systems. However, existing simulators often fall short in diverse scenarios or interactive behavior models for traffic participants. This deficiency underscores the need for a flexible, reliable, user-friendly open-source simulator. Addressing this challenge, Tactics2D adopts a modular approach to traffic scenario construction, encompassing road elements, traffic regulations, behavior models, physics simulations for vehicles, and event detection mechanisms. By integrating numerous commonly utilized algorithms and configurations, Tactics2D empowers users to construct their driving scenarios effortlessly, just like assembling building blocks. Users can effectively evaluate the performance of driving decision-making models across various scenarios by leveraging both public datasets and user-collected real-world data. For access to the source code and community support, please visit the official GitHub page for Tactics2D at https://github.com/WoodOxen/Tactics2D.
Understanding events in texts is a core objective of natural language understanding, which requires detecting event occurrences, extracting event arguments, and analyzing inter-event relationships. However, due to the annotation challenges brought by task complexity, a large-scale dataset covering the full process of event understanding has long been absent. In this paper, we introduce MAVEN-Arg, which augments MAVEN datasets with event argument annotations, making the first all-in-one dataset supporting event detection, event argument extraction (EAE), and event relation extraction. As an EAE benchmark, MAVEN-Arg offers three main advantages: (1) a comprehensive schema covering 162 event types and 612 argument roles, all with expert-written definitions and examples; (2) a large data scale, containing 98,591 events and 290,613 arguments obtained with laborious human annotation; (3) the exhaustive annotation supporting all task variants of EAE, which annotates both entity and non-entity event arguments in document level. Experiments indicate that MAVEN-Arg is quite challenging for both fine-tuned EAE models and proprietary large language models (LLMs). Furthermore, to demonstrate the benefits of an all-in-one dataset, we preliminarily explore a potential application, future event prediction, with LLMs. MAVEN-Arg and codes can be obtained from https://github.com/THU-KEG/MAVEN-Argument.
Patients being admitted to a hospital will most often be associated with a certain clinical development during their stay. However, there is always a risk of patients being subject to the wrong diagnosis or to a certain treatment not pertaining to the desired effect, potentially leading to adverse events. Our research aims to develop an anomaly detection system for identifying deviations from expected clinical trajectories. To address this goal we analyzed 16 months of vital sign recordings obtained from the Nordland Hospital Trust (NHT). We employed an self-supervised framework based on the STraTS transformer architecture to represent the time series data in a latent space. These representations were then subjected to various clustering techniques to explore potential patient phenotypes based on their clinical progress. While our preliminary results from this ongoing research are promising, they underscore the importance of enhancing the dataset with additional demographic information from patients. This additional data will be crucial for a more comprehensive evaluation of the method's performance.