Adversarial examples generated by a surrogate model typically exhibit limited transferability to unknown target systems. To address this problem, many transferability enhancement approaches (e.g., input transformation and model augmentation) have been proposed. However, they show poor performances in attacking systems having different model genera from the surrogate model. In this paper, we propose a novel and generic attacking strategy, called Deformation-Constrained Warping Attack (DeCoWA), that can be effectively applied to cross model genus attack. Specifically, DeCoWA firstly augments input examples via an elastic deformation, namely Deformation-Constrained Warping (DeCoW), to obtain rich local details of the augmented input. To avoid severe distortion of global semantics led by random deformation, DeCoW further constrains the strength and direction of the warping transformation by a novel adaptive control strategy. Extensive experiments demonstrate that the transferable examples crafted by our DeCoWA on CNN surrogates can significantly hinder the performance of Transformers (and vice versa) on various tasks, including image classification, video action recognition, and audio recognition. Code is made available at https://github.com/LinQinLiang/DeCoWA.
WHO's report on environmental noise estimates that 22 M people suffer from chronic annoyance related to noise caused by audio events (AEs) from various sources. Annoyance may lead to health issues and adverse effects on metabolic and cognitive systems. In cities, monitoring noise levels does not provide insights into noticeable AEs, let alone their relations to annoyance. To create annoyance-related monitoring, this paper proposes a graph-based model to identify AEs in a soundscape, and explore relations between diverse AEs and human-perceived annoyance rating (AR). Specifically, this paper proposes a lightweight multi-level graph learning (MLGL) based on local and global semantic graphs to simultaneously perform audio event classification (AEC) and human annoyance rating prediction (ARP). Experiments show that: 1) MLGL with 4.1 M parameters improves AEC and ARP results by using semantic node information in local and global context aware graphs; 2) MLGL captures relations between coarse and fine-grained AEs and AR well; 3) Statistical analysis of MLGL results shows that some AEs from different sources significantly correlate with AR, which is consistent with previous research on human perception of these sound sources.
Soundscape studies typically attempt to capture the perception and understanding of sonic environments by surveying users. However, for long-term monitoring or assessing interventions, sound-signal-based approaches are required. To this end, most previous research focused on psycho-acoustic quantities or automatic sound recognition. Few attempts were made to include appraisal (e.g., in circumplex frameworks). This paper proposes an artificial intelligence (AI)-based dual-branch convolutional neural network with cross-attention-based fusion (DCNN-CaF) to analyze automatic soundscape characterization, including sound recognition and appraisal. Using the DeLTA dataset containing human-annotated sound source labels and perceived annoyance, the DCNN-CaF is proposed to perform sound source classification (SSC) and human-perceived annoyance rating prediction (ARP). Experimental findings indicate that (1) the proposed DCNN-CaF using loudness and Mel features outperforms the DCNN-CaF using only one of them. (2) The proposed DCNN-CaF with cross-attention fusion outperforms other typical AI-based models and soundscape-related traditional machine learning methods on the SSC and ARP tasks. (3) Correlation analysis reveals that the relationship between sound sources and annoyance is similar for humans and the proposed AI-based DCNN-CaF model. (4) Generalization tests show that the proposed model's ARP in the presence of model-unknown sound sources is consistent with expert expectations and can explain previous findings from the literature on sound-scape augmentation.
Most deep learning-based acoustic scene classification (ASC) approaches identify scenes based on acoustic features converted from audio clips containing mixed information entangled by polyphonic audio events (AEs). However, these approaches have difficulties in explaining what cues they use to identify scenes. This paper conducts the first study on disclosing the relationship between real-life acoustic scenes and semantic embeddings from the most relevant AEs. Specifically, we propose an event-relational graph representation learning (ERGL) framework for ASC to classify scenes, and simultaneously answer clearly and straightly which cues are used in classifying. In the event-relational graph, embeddings of each event are treated as nodes, while relationship cues derived from each pair of nodes are described by multi-dimensional edge features. Experiments on a real-life ASC dataset show that the proposed ERGL achieves competitive performance on ASC by learning embeddings of only a limited number of AEs. The results show the feasibility of recognizing diverse acoustic scenes based on the audio event-relational graph. Visualizations of graph representations learned by ERGL are available here (https://github.com/Yuanbo2020/ERGL).
Sound events in daily life carry rich information about the objective world. The composition of these sounds affects the mood of people in a soundscape. Most previous approaches only focus on classifying and detecting audio events and scenes, but may ignore their perceptual quality that may impact humans' listening mood for the environment, e.g. annoyance. To this end, this paper proposes a novel hierarchical graph representation learning (HGRL) approach which links objective audio events (AE) with subjective annoyance ratings (AR) of the soundscape perceived by humans. The hierarchical graph consists of fine-grained event (fAE) embeddings with single-class event semantics, coarse-grained event (cAE) embeddings with multi-class event semantics, and AR embeddings. Experiments show the proposed HGRL successfully integrates AE with AR for AEC and ARP tasks, while coordinating the relations between cAE and fAE and further aligning the two different grains of AE information with the AR.
Most existing deep learning-based acoustic scene classification (ASC) approaches directly utilize representations extracted from spectrograms to identify target scenes. However, these approaches pay little attention to the audio events occurring in the scene despite they provide crucial semantic information. This paper conducts the first study that investigates whether real-life acoustic scenes can be reliably recognized based only on the features that describe a limited number of audio events. To model the task-specific relationships between coarse-grained acoustic scenes and fine-grained audio events, we propose an event relational graph representation learning (ERGL) framework for ASC. Specifically, ERGL learns a graph representation of an acoustic scene from the input audio, where the embedding of each event is treated as a node, while the relationship cues derived from each pair of event embeddings are described by a learned multidimensional edge feature. Experiments on a polyphonic acoustic scene dataset show that the proposed ERGL achieves competitive performance on ASC by using only a limited number of embeddings of audio events without any data augmentations. The validity of the proposed ERGL framework proves the feasibility of recognizing diverse acoustic scenes based on the event relational graph. Our code is available on our homepage (https://github.com/Yuanbo2020/ERGL).
Audio tagging aims to assign predefined tags to audio clips to indicate the class information of audio events. Sequential audio tagging (SAT) means detecting both the class information of audio events, and the order in which they occur within the audio clip. Most existing methods for SAT are based on connectionist temporal classification (CTC). However, CTC cannot effectively capture connections between events due to the conditional independence assumption between outputs at different times. The contextual Transformer (cTransformer) addresses this issue by exploiting contextual information in SAT. Nevertheless, cTransformer is also limited in exploiting contextual information as it only uses forward information in inference. This paper proposes a gated contextual Transformer (GCT) with forward-backward inference (FBI). In addition, a gated contextual multi-layer perceptron (GCMLP) block is proposed in GCT to improve the performance of cTransformer structurally. Experiments on two real-life audio datasets show that the proposed GCT with GCMLP and FBI performs better than the CTC-based methods and cTransformer. To promote research on SAT, the manually annotated sequential labels for the two datasets are released.
Previous works on scene classification are mainly based on audio or visual signals, while humans perceive the environmental scenes through multiple senses. Recent studies on audio-visual scene classification separately fine-tune the largescale audio and image pre-trained models on the target dataset, then either fuse the intermediate representations of the audio model and the visual model, or fuse the coarse-grained decision of both models at the clip level. Such methods ignore the detailed audio events and visual objects in audio-visual scenes (AVS), while humans often identify different scenes through audio events and visual objects within and the congruence between them. To exploit the fine-grained information of audio events and visual objects in AVS, and coordinate the implicit relationship between audio events and visual objects, this paper proposes a multibranch model equipped with contrastive event-object alignment (CEOA) and semantic-based fusion (SF) for AVSC. CEOA aims to align the learned embeddings of audio events and visual objects by comparing the difference between audio-visual event-object pairs. Then, visual objects associated with certain audio events and vice versa are accentuated by cross-attention and undergo SF for semantic-level fusion. Experiments show that: 1) the proposed AVSC model equipped with CEOA and SF outperforms the results of audio-only and visual-only models, i.e., the audio-visual results are better than the results from a single modality. 2) CEOA aligns the embeddings of audio events and related visual objects on a fine-grained level, and the SF effectively integrates both; 3) Compared with other large-scale integrated systems, the proposed model shows competitive performance, even without using additional datasets and data augmentation tricks.
Models based on diverse attention mechanisms have recently shined in tasks related to acoustic event classification (AEC). Among them, self-attention is often used in audio-only tasks to help the model recognize different acoustic events. Self-attention relies on the similarity between time frames, and uses global information from the whole segment to highlight specific features within a frame. In real life, information related to acoustic events will attenuate over time, which means the information within some frames around the event deserves more attention than distant time global information that may be unrelated to the event. This paper shows that self-attention may over-enhance certain segments of audio representations, and smooth out the boundaries between events representations and background noises. Hence, this paper proposes an event-related data conditioning (EDC) for AEC. EDC directly works on spectrograms. The idea of EDC is to adaptively select the frame-related attention range based on acoustic features, and gather the event-related local information to represent the frame. Experiments show that: 1) compared with spectrogram-based data augmentation methods and trainable feature weighting and self-attention, EDC outperforms them in both the original-size mode and the augmented mode; 2) EDC effectively gathers event-related local information and enhances boundaries between events and backgrounds, improving the performance of AEC.
In real life, acoustic scenes and audio events are naturally correlated. Humans instinctively rely on fine-grained audio events as well as the overall sound characteristics to distinguish diverse acoustic scenes. Yet, most previous approaches treat acoustic scene classification (ASC) and audio event classification (AEC) as two independent tasks. A few studies on scene and event joint classification either use synthetic audio datasets that hardly match the real world, or simply use the multi-task framework to perform two tasks at the same time. Neither of these two ways makes full use of the implicit and inherent relation between fine-grained events and coarse-grained scenes. To this end, this paper proposes a relation-guided ASC (RGASC) model to further exploit and coordinate the scene-event relation for the mutual benefit of scene and event recognition. The TUT Urban Acoustic Scenes 2018 dataset (TUT2018) is annotated with pseudo labels of events by a simple and efficient audio-related pre-trained model PANN, which is one of the state-of-the-art AEC models. Then, a prior scene-event relation matrix is defined as the average probability of the presence of each event type in each scene class. Finally, the two-tower RGASC model is jointly trained on the real-life dataset TUT2018 for both scene and event classification. The following results are achieved. 1) RGASC effectively coordinates the true information of coarse-grained scenes and the pseudo information of fine-grained events. 2) The event embeddings learned from pseudo labels under the guidance of prior scene-event relations help reduce the confusion between similar acoustic scenes. 3) Compared with other (non-ensemble) methods, RGASC improves the scene classification accuracy on the real-life dataset.