Traditionally, in paralinguistic analysis for emotion detection from speech, emotions have been identified with discrete or dimensional (continuous-valued) labels. Accordingly, models that have been proposed for emotion detection use one or the other of these label types. However, psychologists like Russell and Plutchik have proposed theories and models that unite these views, maintaining that these representations have shared and complementary information. This paper is an attempt to validate these viewpoints computationally. To this end, we propose a model to jointly predict continuous and discrete emotional attributes and show how the relationship between these can be utilized to improve the robustness and performance of emotion recognition tasks. Our approach comprises multi-task and hierarchical multi-task learning frameworks that jointly model the relationships between continuous-valued and discrete emotion labels. Experimental results on two widely used datasets (IEMOCAP and MSPPodcast) for speech-based emotion recognition show that our model results in statistically significant improvements in performance over strong baselines with non-unified approaches. We also demonstrate that using one type of label (discrete or continuous-valued) for training improves recognition performance in tasks that use the other type of label. Experimental results and reasoning for this approach (called the mismatched training approach) are also presented.
Whisper is a recent Automatic Speech Recognition (ASR) model displaying impressive robustness to both out-of-distribution inputs and random noise. In this work, we show that this robustness does not carry over to adversarial noise. We generate very small input perturbations with Signal Noise Ratio of up to 45dB, with which we can degrade Whisper performance dramatically, or even transcribe a target sentence of our choice. We also show that by fooling the Whisper language detector we can very easily degrade the performance of multilingual models. These vulnerabilities of a widely popular open-source model have practical security implications, and emphasize the need for adversarially robust ASR.
Automatic Speaker Diarization (ASD) is an enabling technology with numerous applications, which deals with recordings of multiple speakers, raising special concerns in terms of privacy. In fact, in remote settings, where recordings are shared with a server, clients relinquish not only the privacy of their conversation, but also of all the information that can be inferred from their voices. However, to the best of our knowledge, the development of privacy-preserving ASD systems has been overlooked thus far. In this work, we tackle this problem using a combination of two cryptographic techniques, Secure Multiparty Computation (SMC) and Secure Modular Hashing, and apply them to the two main steps of a cascaded ASD system: speaker embedding extraction and agglomerative hierarchical clustering. Our system is able to achieve a reasonable trade-off between performance and efficiency, presenting real-time factors of 1.1 and 1.6, for two different SMC security settings.
Temporal action proposal generation (TAPG) is a challenging task, which requires localizing action intervals in an untrimmed video. Intuitively, we as humans, perceive an action through the interactions between actors, relevant objects, and the surrounding environment. Despite the significant progress of TAPG, a vast majority of existing methods ignore the aforementioned principle of the human perceiving process by applying a backbone network into a given video as a black-box. In this paper, we propose to model these interactions with a multi-modal representation network, namely, Actors-Objects-Environment Interaction Network (AOE-Net). Our AOE-Net consists of two modules, i.e., perception-based multi-modal representation (PMR) and boundary-matching module (BMM). Additionally, we introduce adaptive attention mechanism (AAM) in PMR to focus only on main actors (or relevant objects) and model the relationships among them. PMR module represents each video snippet by a visual-linguistic feature, in which main actors and surrounding environment are represented by visual information, whereas relevant objects are depicted by linguistic features through an image-text model. BMM module processes the sequence of visual-linguistic features as its input and generates action proposals. Comprehensive experiments and extensive ablation studies on ActivityNet-1.3 and THUMOS-14 datasets show that our proposed AOE-Net outperforms previous state-of-the-art methods with remarkable performance and generalization for both TAPG and temporal action detection. To prove the robustness and effectiveness of AOE-Net, we further conduct an ablation study on egocentric videos, i.e. EPIC-KITCHENS 100 dataset. Source code is available upon acceptance.
A targeted adversarial attack produces audio samples that can force an Automatic Speech Recognition (ASR) system to output attacker-chosen text. To exploit ASR models in real-world, black-box settings, an adversary can leverage the transferability property, i.e. that an adversarial sample produced for a proxy ASR can also fool a different remote ASR. However recent work has shown that transferability against large ASR models is very difficult. In this work, we show that modern ASR architectures, specifically ones based on Self-Supervised Learning, are in fact vulnerable to transferability. We successfully demonstrate this phenomenon by evaluating state-of-the-art self-supervised ASR models like Wav2Vec2, HuBERT, Data2Vec and WavLM. We show that with low-level additive noise achieving a 30dB Signal-Noise Ratio, we can achieve target transferability with up to 80% accuracy. Next, we 1) use an ablation study to show that Self-Supervised learning is the main cause of that phenomenon, and 2) we provide an explanation for this phenomenon. Through this we show that modern ASR architectures are uniquely vulnerable to adversarial security threats.
Semi-supervised learning (SSL) improves model generalization by leveraging massive unlabeled data to augment limited labeled samples. However, currently, popular SSL evaluation protocols are often constrained to computer vision (CV) tasks. In addition, previous work typically trains deep neural networks from scratch, which is time-consuming and environmentally unfriendly. To address the above issues, we construct a Unified SSL Benchmark (USB) by selecting 15 diverse, challenging, and comprehensive tasks from CV, natural language processing (NLP), and audio processing (Audio), on which we systematically evaluate dominant SSL methods, and also open-source a modular and extensible codebase for fair evaluation on these SSL methods. We further provide pre-trained versions of the state-of-the-art neural models for CV tasks to make the cost affordable for further tuning. USB enables the evaluation of a single SSL algorithm on more tasks from multiple domains but with less cost. Specifically, on a single NVIDIA V100, only 37 GPU days are required to evaluate FixMatch on 15 tasks in USB while 335 GPU days (279 GPU days on 4 CV datasets except for ImageNet) are needed on 5 CV tasks with the typical protocol.
Video instance segmentation (VIS) aims at classifying, segmenting and tracking object instances in video sequences. Recent transformer-based neural networks have demonstrated their powerful capability of modeling spatio-temporal correlations for the VIS task. Relying on video- or clip-level input, they suffer from high latency and computational cost. We propose a robust context fusion network to tackle VIS in an online fashion, which predicts instance segmentation frame-by-frame with a few preceding frames. To acquire the precise and temporal-consistent prediction for each frame efficiently, the key idea is to fuse effective and compact context from reference frames into the target frame. Considering the different effects of reference and target frames on the target prediction, we first summarize contextual features through importance-aware compression. A transformer encoder is adopted to fuse the compressed context. Then, we leverage an order-preserving instance embedding to convey the identity-aware information and correspond the identities to predicted instance masks. We demonstrate that our robust fusion network achieves the best performance among existing online VIS methods and is even better than previously published clip-level methods on the Youtube-VIS 2019 and 2021 benchmarks. In addition, visual objects often have acoustic signatures that are naturally synchronized with them in audio-bearing video recordings. By leveraging the flexibility of our context fusion network on multi-modal data, we further investigate the influence of audios on the video-dense prediction task, which has never been discussed in existing works. We build up an Audio-Visual Instance Segmentation dataset, and demonstrate that acoustic signals in the wild scenarios could benefit the VIS task.
While deep learning based speech enhancement systems have made rapid progress in improving the quality of speech signals, they can still produce outputs that contain artifacts and can sound unnatural. We propose a novel approach to speech enhancement aimed at improving perceptual quality and naturalness of enhanced signals by optimizing for key characteristics of speech. We first identify key acoustic parameters that have been found to correlate well with voice quality (e.g. jitter, shimmer, and spectral flux) and then propose objective functions which are aimed at reducing the difference between clean speech and enhanced speech with respect to these features. The full set of acoustic features is the extended Geneva Acoustic Parameter Set (eGeMAPS), which includes 25 different attributes associated with perception of speech. Given the non-differentiable nature of these feature computation, we first build differentiable estimators of the eGeMAPS and then use them to fine-tune existing speech enhancement systems. Our approach is generic and can be applied to any existing deep learning based enhancement systems to further improve the enhanced speech signals. Experimental results conducted on the Deep Noise Suppression (DNS) Challenge dataset shows that our approach can improve the state-of-the-art deep learning based enhancement systems.
Robustness to adversarial attack is typically evaluated with adversarial accuracy. This metric is however too coarse to properly capture all robustness properties of machine learning models. Many defenses, when evaluated against a strong attack, do not provide accuracy improvements while still contributing partially to adversarial robustness. Popular certification methods suffer from the same issue, as they provide a lower bound to accuracy. To capture finer robustness properties we propose a new metric for L2 robustness, adversarial angular sparsity, which partially answers the question "how many adversarial examples are there around an input". We demonstrate its usefulness by evaluating both "strong" and "weak" defenses. We show that some state-of-the-art defenses, delivering very similar accuracy, can have very different sparsity on the inputs that they are not robust on. We also show that some weak defenses actually decrease robustness, while others strengthen it in a measure that accuracy cannot capture. These differences are predictive of how useful such defenses can become when combined with adversarial training.
Referring video object segmentation (R-VOS) aims to segment the object masks in a video given a referring linguistic expression to the object. It is a recently introduced task attracting growing research attention. However, all existing works make a strong assumption: The object depicted by the expression must exist in the video, namely, the expression and video must have an object-level semantic consensus. This is often violated in real-world applications where an expression can be queried to false videos, and existing methods always fail in such false queries due to abusing the assumption. In this work, we emphasize that studying semantic consensus is necessary to improve the robustness of R-VOS. Accordingly, we pose an extended task from R-VOS without the semantic consensus assumption, named Robust R-VOS ($\mathrm{R}^2$-VOS). The $\mathrm{R}^2$-VOS task is essentially related to the joint modeling of the primary R-VOS task and its dual problem (text reconstruction). We embrace the observation that the embedding spaces have relational consistency through the cycle of text-video-text transformation, which connects the primary and dual problems. We leverage the cycle consistency to discriminate the semantic consensus, thus advancing the primary task. Parallel optimization of the primary and dual problems are enabled by introducing an early grounding medium. A new evaluation dataset, $\mathrm{R}^2$-Youtube-VOS, is collected to measure the robustness of R-VOS models against unpaired videos and expressions. Extensive experiments demonstrate that our method not only identifies negative pairs of unrelated expressions and videos, but also improves the segmentation accuracy for positive pairs with a superior disambiguating ability. Our model achieves the state-of-the-art performance on Ref-DAVIS17, Ref-Youtube-VOS, and the novel $\mathrm{R}^2$-Youtube-VOS dataset.