Stuttering is a neurodevelopmental speech disorder characterized by common speech symptoms such as pauses, exclamations, repetition, and prolongation. Speech-language pathologists typically assess the type and severity of stuttering by observing these symptoms. Many effective end-to-end methods exist for stuttering detection, but a commonly overlooked challenge is the uncertain relationship between tasks involved in this process. Using a suitable multi-task strategy could improve stuttering detection performance. This paper presents a novel stuttering event detection model designed to help speech-language pathologists assess both the type and severity of stuttering. First, the Conformer model extracts acoustic features from stuttered speech, followed by a Long Short-Term Memory (LSTM) network to capture contextual information. Finally, we explore multi-task learning for stuttering and propose an effective multi-task strategy. Experimental results show that our model outperforms current state-of-the-art methods for stuttering detection. In the SLT 2024 Stuttering Speech Challenge based on the AS-70 dataset [1], our model improved the mean F1 score by 24.8% compared to the baseline method and achieved first place. On this basis, we conducted relevant extensive experiments on LSTM and multi-task learning strategies respectively. The results show that our proposed method improved the mean F1 score by 39.8% compared to the baseline method.
Detecting and tracking emerging trends and weak signals in large, evolving text corpora is vital for applications such as monitoring scientific literature, managing brand reputation, surveilling critical infrastructure and more generally to any kind of text-based event detection. Existing solutions often fail to capture the nuanced context or dynamically track evolving patterns over time. BERTrend, a novel method, addresses these limitations using neural topic modeling in an online setting. It introduces a new metric to quantify topic popularity over time by considering both the number of documents and update frequency. This metric classifies topics as noise, weak, or strong signals, flagging emerging, rapidly growing topics for further investigation. Experimentation on two large real-world datasets demonstrates BERTrend's ability to accurately detect and track meaningful weak signals while filtering out noise, offering a comprehensive solution for monitoring emerging trends in large-scale, evolving text corpora. The method can also be used for retrospective analysis of past events. In addition, the use of Large Language Models together with BERTrend offers efficient means for the interpretability of trends of events.
Sound Event Detection (SED) is challenging in noisy environments where overlapping sounds obscure target events. Language-queried audio source separation (LASS) aims to isolate the target sound events from a noisy clip. However, this approach can fail when the exact target sound is unknown, particularly in noisy test sets, leading to reduced performance. To address this issue, we leverage the capabilities of large language models (LLMs) to analyze and summarize acoustic data. By using LLMs to identify and select specific noise types, we implement a noise augmentation method for noise-robust fine-tuning. The fine-tuned model is applied to predict clip-wise event predictions as text queries for the LASS model. Our studies demonstrate that the proposed method improves SED performance in noisy environments. This work represents an early application of LLMs in noise-robust SED and suggests a promising direction for handling overlapping events in SED. Codes and pretrained models are available at https://github.com/apple-yinhan/Noise-robust-SED.
Autonomous Vehicle (AV) perception systems require more than simply seeing, via e.g., object detection or scene segmentation. They need a holistic understanding of what is happening within the scene for safe interaction with other road users. Few datasets exist for the purpose of developing and training algorithms to comprehend the actions of other road users. This paper presents ROAD-Waymo, an extensive dataset for the development and benchmarking of techniques for agent, action, location and event detection in road scenes, provided as a layer upon the (US) Waymo Open dataset. Considerably larger and more challenging than any existing dataset (and encompassing multiple cities), it comes with 198k annotated video frames, 54k agent tubes, 3.9M bounding boxes and a total of 12.4M labels. The integrity of the dataset has been confirmed and enhanced via a novel annotation pipeline designed for automatically identifying violations of requirements specifically designed for this dataset. As ROAD-Waymo is compatible with the original (UK) ROAD dataset, it provides the opportunity to tackle domain adaptation between real-world road scenarios in different countries within a novel benchmark: ROAD++.
We introduce the Seismic Language Model (SeisLM), a foundational model designed to analyze seismic waveforms -- signals generated by Earth's vibrations such as the ones originating from earthquakes. SeisLM is pretrained on a large collection of open-source seismic datasets using a self-supervised contrastive loss, akin to BERT in language modeling. This approach allows the model to learn general seismic waveform patterns from unlabeled data without being tied to specific downstream tasks. When fine-tuned, SeisLM excels in seismological tasks like event detection, phase-picking, onset time regression, and foreshock-aftershock classification. The code has been made publicly available on https://github.com/liutianlin0121/seisLM.
Continual Event Detection (CED) poses a formidable challenge due to the catastrophic forgetting phenomenon, where learning new tasks (with new coming event types) hampers performance on previous ones. In this paper, we introduce a novel approach, Lifelong Event Detection via Optimal Transport (LEDOT), that leverages optimal transport principles to align the optimization of our classification module with the intrinsic nature of each class, as defined by their pre-trained language modeling. Our method integrates replay sets, prototype latent representations, and an innovative Optimal Transport component. Extensive experiments on MAVEN and ACE datasets demonstrate LEDOT's superior performance, consistently outperforming state-of-the-art baselines. The results underscore LEDOT as a pioneering solution in continual event detection, offering a more effective and nuanced approach to addressing catastrophic forgetting in evolving environments.
Domain shifts are ubiquitous in machine learning, and can substantially degrade a model's performance when deployed to real-world data. To address this, distribution alignment methods aim to learn feature representations which are invariant across domains, by minimising the discrepancy between the distributions. However, the discrepancy estimates can be extremely noisy when training via stochastic gradient descent (SGD), and shifts in the relative proportions of different subgroups can lead to domain misalignments; these can both stifle the benefits of the method. This paper proposes to improve these estimates by inducing diversity in each sampled minibatch. This simultaneously balances the data and reduces the variance of the gradients, thereby enhancing the model's generalisation ability. We describe two options for diversity-based data samplers, based on the k-determinantal point process (k-DPP) and the k-means++ algorithm, which can function as drop-in replacements for a standard random sampler. On a real-world domain shift task of bioacoustic event detection, we show that both options 1) yield minibatches which are more representative of the full dataset; 2) reduce the distance estimation error between distributions, for a given sample size; and 3) improve out-of-distribution accuracy for two distribution alignment algorithms, as well as standard ERM.
Artificial intelligence (AI) has demonstrated significant potential in ECG analysis and cardiovascular disease assessment. Recently, foundation models have played a remarkable role in advancing medical AI. The development of an ECG foundation model holds the promise of elevating AI-ECG research to new heights. However, building such a model faces several challenges, including insufficient database sample sizes and inadequate generalization across multiple domains. Additionally, there is a notable performance gap between single-lead and multi-lead ECG analyses. We introduced an ECG Foundation Model (ECGFounder), a general-purpose model that leverages real-world ECG annotations from cardiology experts to broaden the diagnostic capabilities of ECG analysis. ECGFounder was trained on over 10 million ECGs with 150 label categories from the Harvard-Emory ECG Database, enabling comprehensive cardiovascular disease diagnosis through ECG analysis. The model is designed to be both an effective out-of-the-box solution, and a to be fine-tunable for downstream tasks, maximizing usability. Importantly, we extended its application to lower rank ECGs, and arbitrary single-lead ECGs in particular. ECGFounder is applicable to supporting various downstream tasks in mobile monitoring scenarios. Experimental results demonstrate that ECGFounder achieves expert-level performance on internal validation sets, with AUROC exceeding 0.95 for eighty diagnoses. It also shows strong classification performance and generalization across various diagnoses on external validation sets. When fine-tuned, ECGFounder outperforms baseline models in demographic analysis, clinical event detection, and cross-modality cardiac rhythm diagnosis. The trained model and data will be publicly released upon publication through the bdsp.io. Our code is available at https://github.com/PKUDigitalHealth/ECGFounder
In sound event detection (SED), overlapping sound events pose a significant challenge, as certain events can be easily masked by background noise or other events, resulting in poor detection performance. To address this issue, we propose the text-queried SED (TQ-SED) framework. Specifically, we first pre-train a language-queried audio source separation (LASS) model to separate the audio tracks corresponding to different events from the input audio. Then, multiple target SED branches are employed to detect individual events. AudioSep is a state-of-the-art LASS model, but has limitations in extracting dynamic audio information because of its pure convolutional structure for separation. To address this, we integrate a dual-path recurrent neural network block into the model. We refer to this structure as AudioSep-DP, which achieves the first place in DCASE 2024 Task 9 on language-queried audio source separation (objective single model track). Experimental results show that TQ-SED can significantly improve the SED performance, with an improvement of 7.22\% on F1 score over the conventional framework. Additionally, we setup comprehensive experiments to explore the impact of model complexity. The source code and pre-trained model are released at https://github.com/apple-yinhan/TQ-SED.
Sensors are widely used in many applications, acting as a link between the physical and digital domains. However, the sensor output is often affected by external factors such as noise, interference, drifts, and non-linearities, making it challenging for accurate signal and event detection. To address this issue, a novel approach to model a sensor using an adaptive filter based on the β-divergence inspired cost function is proposed to make the sensor robust against changing environmental conditions over time. The proposed β-divergence based least mean square (βLMS) algorithm can effectively analyze and compensate for external influences in sensor output, leading to a more dependable and precise representation of sensor behavior while maintaining computational efficiency. Additionally, the mean and mean-square stability bounds are determined to establish the acceptable range of learning rates for the βLMS algorithm. Furthermore, this paper examines the transient, steady-state, tracking performance, and robustness of the proposed βLMS algorithm. Moreover, the performance of the proposed βLMS algorithm is assessed through simulation study, demonstrating its efficacy in various real-world applications of sensors such as system identification, missile tracking, and active noise cancellation. The hardware implementation is also carried out to validate the performance of the proposed βLMS algorithm in real-time scenario to model high-cost sensor behavior using low-cost sensors. The results indicate that the proposed βLMS algorithm significantly enhances the performance of the sensors in practical applications.
This study aims to comprehensively review and empirically evaluate the application of multimodal large language models (MLLMs) and Large Vision Models (VLMs) in object detection for transportation systems. In the first fold, we provide a background about the potential benefits of MLLMs in transportation applications and conduct a comprehensive review of current MLLM technologies in previous studies. We highlight their effectiveness and limitations in object detection within various transportation scenarios. The second fold involves providing an overview of the taxonomy of end-to-end object detection in transportation applications and future directions. Building on this, we proposed empirical analysis for testing MLLMs on three real-world transportation problems that include object detection tasks namely, road safety attributes extraction, safety-critical event detection, and visual reasoning of thermal images. Our findings provide a detailed assessment of MLLM performance, uncovering both strengths and areas for improvement. Finally, we discuss practical limitations and challenges of MLLMs in enhancing object detection in transportation, thereby offering a roadmap for future research and development in this critical area.
A significant challenge in sound event detection (SED) is the effective utilization of unlabeled data, given the limited availability of labeled data due to high annotation costs. Semi-supervised algorithms rely on labeled data to learn from unlabeled data, and the performance is constrained by the quality and size of the former. In this paper, we introduce the Prototype based Masked Audio Model~(PMAM) algorithm for self-supervised representation learning in SED, to better exploit unlabeled data. Specifically, semantically rich frame-level pseudo labels are constructed from a Gaussian mixture model (GMM) based prototypical distribution modeling. These pseudo labels supervise the learning of a Transformer-based masked audio model, in which binary cross-entropy loss is employed instead of the widely used InfoNCE loss, to provide independent loss contributions from different prototypes, which is important in real scenarios in which multiple labels may apply to unsupervised data frames. A final stage of fine-tuning with just a small amount of labeled data yields a very high performing SED model. On like-for-like tests using the DESED task, our method achieves a PSDS1 score of 62.5\%, surpassing current state-of-the-art models and demonstrating the superiority of the proposed technique.
The removal of carefully-selected examples from training data has recently emerged as an effective way of improving the robustness of machine learning models. However, the best way to select these examples remains an open question. In this paper, we consider the problem from the perspective of unsupervised domain adaptation (UDA). We propose AdaPrune, a method for UDA whereby training examples are removed to attempt to align the training distribution to that of the target data. By adopting the maximum mean discrepancy (MMD) as the criterion for alignment, the problem can be neatly formulated and solved as an integer quadratic program. We evaluate our approach on a real-world domain shift task of bioacoustic event detection. As a method for UDA, we show that AdaPrune outperforms related techniques, and is complementary to other UDA algorithms such as CORAL. Our analysis of the relationship between the MMD and model accuracy, along with t-SNE plots, validate the proposed method as a principled and well-founded way of performing data pruning.
This paper presents a residential audio dataset to support sound event detection research for smart home applications aimed at promoting wellbeing for older adults. The dataset is constructed by deploying audio recording systems in the homes of 8 participants aged 55-80 years for a 7-day period. Acoustic characteristics are documented through detailed floor plans and construction material information to enable replication of the recording environments for AI model deployment. A novel automated speech removal pipeline is developed, using pre-trained audio neural networks to detect and remove segments containing spoken voice, while preserving segments containing other sound events. The resulting dataset consists of privacy-compliant audio recordings that accurately capture the soundscapes and activities of daily living within residential spaces. The paper details the dataset creation methodology, the speech removal pipeline utilizing cascaded model architectures, and an analysis of the vocal label distribution to validate the speech removal process. This dataset enables the development and benchmarking of sound event detection models tailored specifically for in-home applications.
We propose a pre-training pipeline for audio spectrogram transformers for frame-level sound event detection tasks. On top of common pre-training steps, we add a meticulously designed training routine on AudioSet frame-level annotations. This includes a balanced sampler, aggressive data augmentation, and ensemble knowledge distillation. For five transformers, we obtain a substantial performance improvement over previously available checkpoints both on AudioSet frame-level predictions and on frame-level sound event detection downstream tasks, confirming our pipeline's effectiveness. We publish the resulting checkpoints that researchers can directly fine-tune to build high-performance models for sound event detection tasks.
Sound Event Detection (SED) detects regions of sound events, while Speaker Diarization (SD) segments speech conversations attributed to individual speakers. In SED, all speaker segments are classified as a single speech event, while in SD, non-speech sounds are treated merely as background noise. Thus, both tasks provide only partial analysis in complex audio scenarios involving both speech conversation and non-speech sounds. In this paper, we introduce a novel task called Unified Audio Event Detection (UAED) for comprehensive audio analysis. UAED explores the synergy between SED and SD tasks, simultaneously detecting non-speech sound events and fine-grained speech events based on speaker identities. To tackle this task, we propose a Transformer-based UAED (T-UAED) framework and construct the UAED Data derived from the Librispeech dataset and DESED soundbank. Experiments demonstrate that the proposed framework effectively exploits task interactions and substantially outperforms the baseline that simply combines the outputs of SED and SD models. T-UAED also shows its versatility by performing comparably to specialized models for individual SED and SD tasks on DESED and CALLHOME datasets.
Abnormal event detection or anomaly detection in surveillance videos is currently a challenge because of the diversity of possible events. Due to the lack of anomalous events at training time, anomaly detection requires the design of learning methods without supervision. In this work we propose an unsupervised approach for video anomaly detection with the aim to jointly optimize the objectives of the deep neural network and the anomaly detection task using a hybrid architecture. Initially, a convolutional autoencoder is pre-trained in an unsupervised manner with a fusion of depth, motion and appearance features. In the second step, we utilize the encoder part of the pre-trained autoencoder and extract the embeddings of the fused input. Now, we jointly train/ fine tune the encoder to map the embeddings to a hypercenter. Thus, embeddings of normal data fall near the hypercenter, whereas embeddings of anomalous data fall far away from the hypercenter.
Deep learning systems have become increasingly energy- and computation-intensive, raising concerns about their environmental impact. As organizers of the Detection and Classification of Acoustic Scenes and Events (DCASE) challenge, we recognize the importance of addressing this issue. For the past three years, we have integrated energy consumption metrics into the evaluation of sound event detection (SED) systems. In this paper, we analyze the impact of this energy criterion on the challenge results and explore the evolution of system complexity and energy consumption over the years. We highlight a shift towards more energy-efficient approaches during training without compromising performance, while the number of operations and system complexity continue to grow. Through this analysis, we hope to promote more environmentally friendly practices within the SED community.
The StutteringSpeech Challenge focuses on advancing speech technologies for people who stutter, specifically targeting Stuttering Event Detection (SED) and Automatic Speech Recognition (ASR) in Mandarin. The challenge comprises three tracks: (1) SED, which aims to develop systems for detection of stuttering events; (2) ASR, which focuses on creating robust systems for recognizing stuttered speech; and (3) Research track for innovative approaches utilizing the provided dataset. We utilizes an open-source Mandarin stuttering dataset AS-70, which has been split into new training and test sets for the challenge. This paper presents the dataset, details the challenge tracks, and analyzes the performance of the top systems, highlighting improvements in detection accuracy and reductions in recognition error rates. Our findings underscore the potential of specialized models and augmentation strategies in developing stuttered speech technologies.
Sound Event Detection (SED) plays a vital role in comprehending and perceiving acoustic scenes. Previous methods have demonstrated impressive capabilities. However, they are deficient in learning features of complex scenes from heterogeneous dataset. In this paper, we introduce a novel dual-branch architecture named Mutual-Assistance Tuning and Dual-Branch Aggregating for Heterogeneous Sound Event Detection (MTDA-HSED). The MTDA-HSED architecture employs the Mutual-Assistance Audio Adapter (M3A) to effectively tackle the multi-scenario problem and uses the Dual-Branch Mid-Fusion (DBMF) module to tackle the multi-granularity problem. Specifically, M3A is integrated into the BEATs block as an adapter to improve the BEATs' performance by fine-tuning it on the multi-scenario dataset. The DBMF module connects BEATs and CNN branches, which facilitates the deep fusion of information from the BEATs and the CNN branches. Experimental results show that the proposed methods exceed the baseline of mpAUC by \textbf{$5\%$} on the DESED and MAESTRO Real datasets. Code is available at https://github.com/Visitor-W/MTDA.