Recent research in deep learning-based Sound Event Detection (SED) has primarily focused on Convolutional Recurrent Neural Networks (CRNNs) and Transformer models. However, conventional 2D convolution-based models assume shift invariance along both the temporal and frequency axes, leadin to inconsistencies when dealing with frequency-dependent characteristics of acoustic signals. To address this issue, this study proposes Frequency Dynamic Convolution (FDY conv), which dynamically adjusts convolutional kernels based on the frequency composition of the input signal to enhance SED performance. FDY conv constructs an optimal frequency response by adaptively weighting multiple basis kernels based on frequency-specific attention weights. Experimental results show that applying FDY conv to CRNNs improves performance on the DESED dataset by 7.56% compared to the baseline CRNN. However, FDY conv has limitations in that it combines basis kernels of the same shape across all frequencies, restricting its ability to capture diverse frequency-specific characteristics. Additionally, the $3\times3$ basis kernel size is insufficient to capture a broader frequency range. To overcome these limitations, this study introduces an extended family of FDY conv models. Dilated FDY conv (DFD conv) applies convolutional kernels with various dilation rates to expand the receptive field along the frequency axis and enhance frequency-specific feature representation. Experimental results show that DFD conv improves performance by 9.27% over the baseline. Partial FDY conv (PFD conv) addresses the high computational cost of FDY conv, which results from performing all convolution operations with dynamic kernels. Since FDY conv may introduce unnecessary adaptivity for quasi-stationary sound events, PFD conv integrates standard 2D convolutions with frequency-adaptive kernels to reduce computational complexity while maintaining performance. Experimental results demonstrate that PFD conv improves performance by 7.80% over the baseline while reducing the number of parameters by 54.4% compared to FDY conv. Multi-Dilated FDY conv (MDFD conv) extends DFD conv by addressing its structural limitation of applying the same dilation across all frequencies. By utilizing multiple convolutional kernels with different dilation rates, MDFD conv effectively captures diverse frequency-dependent patterns. Experimental results indicate that MDFD conv achieves the highest performance, improving the baseline CRNN performance by 10.98%. Furthermore, standard FDY conv employs Temporal Average Pooling, which assigns equal weight to all frames along the time axis, limiting its ability to effectively capture transient events. To overcome this, this study proposes TAP-FDY conv (TFD conv), which integrates Temporal Attention Pooling (TA) that focuses on salient features, Velocity Attention Pooling (VA) that emphasizes transient characteristics, and Average Pooling (AP) that captures stationary properties. TAP-FDY conv achieves the same performance as MDFD conv but reduces the number of parameters by approximately 30.01% (12.703M vs. 18.157M), achieving equivalent accuracy with lower computational complexity. Class-wise performance analysis reveals that FDY conv improves detection of non-stationary events, DFD conv is particularly effective for events with broad spectral features, and PFD conv enhances the detection of quasi-stationary events. Additionally, TFD conv (TFD-CRNN) demonstrates strong performance in detecting transient events. In the case studies, PFD conv effectively captures stable signal patterns in tank powertrain fault recognition, DFD conv recognizes wide harmonic spectral patterns on speed-varying motor fault recognition, while TFD conv outperforms other models in detecting transient signals in offshore arc detection. These results suggest that frequency-adaptive convolutions and their extended variants provide a robust alternative to conventional 2D convolutions in deep learning-based audio processing.
Bioacoustic sound event detection (BioSED) is crucial for biodiversity conservation but faces practical challenges during model development and training: limited amounts of annotated data, sparse events, species diversity, and class imbalance. To address these challenges efficiently with a limited labeling budget, we apply the mismatch-first farthest-traversal (MFFT), an active learning method integrating committee voting disagreement and diversity analysis. We also refine an existing BioSED dataset specifically for evaluating active learning algorithms. Experimental results demonstrate that MFFT achieves a mAP of 68% when cold-starting and 71% when warm-starting (which is close to the fully-supervised mAP of 75%) while using only 2.3% of the annotations. Notably, MFFT excels in cold-start scenarios and with rare species, which are critical for monitoring endangered species, demonstrating its practical value.
Self-supervised learning (SSL) models offer powerful representations for sound event detection (SED), yet their synergistic potential remains underexplored. This study systematically evaluates state-of-the-art SSL models to guide optimal model selection and integration for SED. We propose a framework that combines heterogeneous SSL representations (e.g., BEATs, HuBERT, WavLM) through three fusion strategies: individual SSL embedding integration, dual-modal fusion, and full aggregation. Experiments on the DCASE 2023 Task 4 Challenge reveal that dual-modal fusion (e.g., CRNN+BEATs+WavLM) achieves complementary performance gains, while CRNN+BEATs alone delivers the best results among individual SSL models. We further introduce normalized sound event bounding boxes (nSEBBs), an adaptive post-processing method that dynamically adjusts event boundary predictions, improving PSDS1 by up to 4% for standalone SSL models. These findings highlight the compatibility and complementarity of SSL architectures, providing guidance for task-specific fusion and robust SED system design.
Recent advances in deep learning, particularly frequency dynamic convolution (FDY conv), have significantly improved sound event detection (SED) by enabling frequency-adaptive feature extraction. However, FDY conv relies on temporal average pooling, which treats all temporal frames equally, limiting its ability to capture transient sound events such as alarm bells, door knocks, and speech plosives. To address this limitation, we propose temporal attention pooling frequency dynamic convolution (TFD conv) to replace temporal average pooling with temporal attention pooling (TAP). TAP adaptively weights temporal features through three complementary mechanisms: time attention pooling (TA) for emphasizing salient features, velocity attention pooling (VA) for capturing transient changes, and conventional average pooling for robustness to stationary signals. Ablation studies show that TFD conv improves average PSDS1 by 3.02% over FDY conv with only a 14.8% increase in parameter count. Classwise ANOVA and Tukey HSD analysis further demonstrate that TFD conv significantly enhances detection performance for transient-heavy events, outperforming existing FDY conv models. Notably, TFD conv achieves a maximum PSDS1 score of 0.456, surpassing previous state-of-the-art SED systems. We also explore the compatibility of TAP with other FDY conv variants, including dilated FDY conv (DFD conv), partial FDY conv (PFD conv), and multi-dilated FDY conv (MDFD conv). Among these, the integration of TAP with MDFD conv achieves the best result with a PSDS1 score of 0.459, validating the complementary strengths of temporal attention and multi-scale frequency adaptation. These findings establish TFD conv as a powerful and generalizable framework for enhancing both transient sensitivity and overall feature robustness in SED.
In this paper, we propose a novel formula-driven supervised learning (FDSL) framework for pre-training an environmental sound analysis model by leveraging acoustic signals parametrically synthesized through formula-driven methods. Specifically, we outline detailed procedures and evaluate their effectiveness for sound event detection (SED). The SED task, which involves estimating the types and timings of sound events, is particularly challenged by the difficulty of acquiring a sufficient quantity of accurately labeled training data. Moreover, it is well known that manually annotated labels often contain noises and are significantly influenced by the subjective judgment of annotators. To address these challenges, we propose a novel pre-training method that utilizes a synthetic dataset, Formula-SED, where acoustic data are generated solely based on mathematical formulas. The proposed method enables large-scale pre-training by using the synthesis parameters applied at each time step as ground truth labels, thereby eliminating label noise and bias. We demonstrate that large-scale pre-training with Formula-SED significantly enhances model accuracy and accelerates training, as evidenced by our results in the DESED dataset used for DCASE2023 Challenge Task 4. The project page is at https://yutoshibata07.github.io/Formula-SED/
We target the problem of developing new low-complexity networks for the sound event detection task. Our goal is to meticulously analyze the performance-complexity trade-off, aiming to be competitive with the large state-of-the-art models, at a fraction of the computational requirements. We find that low-complexity convolutional models previously proposed for audio tagging can be effectively adapted for event detection (which requires frame-wise prediction) by adjusting convolutional strides, removing the global pooling, and, importantly, adding a sequence model before the (now frame-wise) classification heads. Systematic experiments reveal that the best choice for the sequence model type depends on which complexity metric is most important for the given application. We also investigate the impact of enhanced training strategies such as knowledge distillation. In the end, we show that combined with an optimized training strategy, we can reach event detection performance comparable to state-of-the-art transformers while requiring only around 5% of the parameters. We release all our pre-trained models and the code for reproducing this work to support future research in low-complexity sound event detection at https://github.com/theMoro/EfficientSED.
The vast amounts of audio data collected in Sound Event Detection (SED) applications require efficient annotation strategies to enable supervised learning. Manual labeling is expensive and time-consuming, making Active Learning (AL) a promising approach for reducing annotation effort. We introduce Top K Entropy, a novel uncertainty aggregation strategy for AL that prioritizes the most uncertain segments within an audio recording, instead of averaging uncertainty across all segments. This approach enables the selection of entire recordings for annotation, improving efficiency in sparse data scenarios. We compare Top K Entropy to random sampling and Mean Entropy, and show that fewer labels can lead to the same model performance, particularly in datasets with sparse sound events. Evaluations are conducted on audio mixtures of sound recordings from parks with meerkat, dog, and baby crying sound events, representing real-world bioacoustic monitoring scenarios. Using Top K Entropy for active learning, we can achieve comparable performance to training on the fully labeled dataset with only 8% of the labels. Top K Entropy outperforms Mean Entropy, suggesting that it is best to let the most uncertain segments represent the uncertainty of an audio file. The findings highlight the potential of AL for scalable annotation in audio and time-series applications, including bioacoustics.
We propose a method for accurately detecting bioacoustic sound events that is robust to overlapping events, a common issue in domains such as ethology, ecology and conservation. While standard methods employ a frame-based, multi-label approach, we introduce an onset-based detection method which we name Voxaboxen. It takes inspiration from object detection methods in computer vision, but simultaneously takes advantage of recent advances in self-supervised audio encoders. For each time window, Voxaboxen predicts whether it contains the start of a vocalization and how long the vocalization is. It also does the same in reverse, predicting whether each window contains the end of a vocalization, and how long ago it started. The two resulting sets of bounding boxes are then fused using a graph-matching algorithm. We also release a new dataset designed to measure performance on detecting overlapping vocalizations. This consists of recordings of zebra finches annotated with temporally-strong labels and showing frequent overlaps. We test Voxaboxen on seven existing data sets and on our new data set. We compare Voxaboxen to natural baselines and existing sound event detection methods and demonstrate SotA results. Further experiments show that improvements are robust to frequent vocalization overlap.
We propose a methodology for training foundation models that enhances their in-context learning capabilities within the domain of bioacoustic signal processing. We use synthetically generated training data, introducing a domain-randomization-based pipeline that constructs diverse acoustic scenes with temporally strong labels. We generate over 8.8 thousand hours of strongly-labeled audio and train a query-by-example, transformer-based model to perform few-shot bioacoustic sound event detection. Our second contribution is a public benchmark of 13 diverse few-shot bioacoustics tasks. Our model outperforms previously published methods by 49%, and we demonstrate that this is due to both model design and data scale. We make our trained model available via an API, to provide ecologists and ethologists with a training-free tool for bioacoustic sound event detection.
Sound event detection (SED) has significantly benefited from self-supervised learning (SSL) approaches, particularly masked audio transformer for SED (MAT-SED), which leverages masked block prediction to reconstruct missing audio segments. However, while effective in capturing global dependencies, masked block prediction disrupts transient sound events and lacks explicit enforcement of temporal order, making it less suitable for fine-grained event boundary detection. To address these limitations, we propose JiTTER (Jigsaw Temporal Transformer for Event Reconstruction), an SSL framework designed to enhance temporal modeling in transformer-based SED. JiTTER introduces a hierarchical temporal shuffle reconstruction strategy, where audio sequences are randomly shuffled at both the block-level and frame-level, forcing the model to reconstruct the correct temporal order. This pretraining objective encourages the model to learn both global event structures and fine-grained transient details, improving its ability to detect events with sharp onset-offset characteristics. Additionally, we incorporate noise injection during block shuffle, providing a subtle perturbation mechanism that further regularizes feature learning and enhances model robustness. Experimental results on the DESED dataset demonstrate that JiTTER outperforms MAT-SED, achieving a 5.89% improvement in PSDS, highlighting the effectiveness of explicit temporal reasoning in SSL-based SED. Our findings suggest that structured temporal reconstruction tasks, rather than simple masked prediction, offer a more effective pretraining paradigm for sound event representation learning.
In this work, various analysis methods are conducted on frequency-dependent methods on SED to further delve into their detailed characteristics and behaviors on SED. While SED has been rapidly advancing through the adoption of various deep learning techniques from other pattern recognition fields, these techniques are often not suitable for SED. To address this issue, two frequency-dependent SED methods were previously proposed: FilterAugment, a data augmentation randomly weighting frequency bands, and frequency dynamic convolution (FDY Conv), an architecture applying frequency adaptive convolution kernels. These methods have demonstrated superior performance in SED, and we aim to further analyze their detailed effectiveness and characteristics in SED. We compare class-wise performance to find out specific pros and cons of FilterAugment and FDY Conv. We apply Gradient-weighted Class Activation Mapping (Grad-CAM), which highlights time-frequency region that is more inferred by the model, on SED models with and without frequency masking and two types of FilterAugment to observe their detailed characteristics. We propose simpler frequency dependent convolution methods and compare them with FDY Conv to further understand which components of FDY Conv affects SED performance. Lastly, we apply PCA to show how FDY Conv adapts dynamic kernel across frequency dimensions on different sound event classes. The results and discussions demonstrate that frequency dependency plays a significant role in sound event detection and further confirms the effectiveness of frequency dependent methods on SED.
This paper investigates automatic epileptic seizure detection from audio recordings using convolutional neural net- works. The labeling and analysis of seizure events are necessary in the medical field for patient monitoring, but the manual annotation by expert annotators is time-consuming and extremely monotonous. The proposed method treats all seizure vocalizations as a single target event class, and models the seizure detection problem in terms of detecting the target vs non-target classes. For detection, the method employs a convolutional neural network trained to detect the seizure events in short time segments, based on mel-energies as feature representation. Experiments carried out with different seizure types on 900 hours of audio recordings from 40 patients show that the proposed approach can detect seizures with over 80% accuracy, with a 13% false positive rate and a 22.8% false negative rate. Index Terms—Epileptic seizure detection, convolutional neural network (CNN), sound event detection, audio processing and analysis.
In traditional sound event localization and detection (SELD) tasks, the focus is typically on sound event detection (SED) and direction-of-arrival (DOA) estimation, but they fall short of providing full spatial information about the sound source. The 3D SELD task addresses this limitation by integrating source distance estimation (SDE), allowing for complete spatial localization. We propose three approaches to tackle this challenge: a novel method with independent training and joint prediction, which firstly treats DOA and distance estimation as separate tasks and then combines them to solve 3D SELD; a dual-branch representation with source Cartesian coordinate used for simultaneous DOA and distance estimation; and a three-branch structure that jointly models SED, DOA, and SDE within a unified framework. Our proposed method ranked first in the DCASE 2024 Challenge Task 3, demonstrating the effectiveness of joint modeling for addressing the 3D SELD task. The relevant code for this paper will be open-sourced in the future.
Weakly Supervised Sound Event Detection (WSSED), which relies on audio tags without precise onset and offset times, has become prevalent due to the scarcity of strongly labeled data that includes exact temporal boundaries for events. This study introduces Frame-level Pseudo Strong Labeling (FPSL) to overcome the lack of temporal information in WSSED by generating pseudo strong labels from frame-level predictions. This enhances temporal localization during training and addresses the limitations of clip-wise weak supervision. We validate our approach across three benchmark datasets (DCASE2017 Task 4, DCASE2018 Task 4, and UrbanSED) and demonstrate significant improvements in key metrics such as the Polyphonic Sound Detection Scores (PSDS), event-based F1 scores, and intersection-based F1 scores. For example, Convolutional Recurrent Neural Networks (CRNNs) trained with FPSL outperform baseline models by 4.9% in PSDS1 on DCASE2017, 7.6% on DCASE2018, and 1.8% on UrbanSED, confirming the effectiveness of our method in enhancing model performance.
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.
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.
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.
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.