Natural human-computer interaction and audio-visual human behaviour sensing systems, which would achieve robust performance in-the-wild are more needed than ever as digital devices are becoming indispensable part of our life more and more. Accurately annotated real-world data are the crux in devising such systems. However, existing databases usually consider controlled settings, low demographic variability, and a single task. In this paper, we introduce the SEWA database of more than 2000 minutes of audio-visual data of 398 people coming from six cultures, 50% female, and uniformly spanning the age range of 18 to 65 years old. Subjects were recorded in two different contexts: while watching adverts and while discussing adverts in a video chat. The database includes rich annotations of the recordings in terms of facial landmarks, facial action units (FAU), various vocalisations, mirroring, and continuously valued valence, arousal, liking, agreement, and prototypic examples of (dis)liking. This database aims to be an extremely valuable resource for researchers in affective computing and automatic human sensing and is expected to push forward the research in human behaviour analysis, including cultural studies. Along with the database, we provide extensive baseline experiments for automatic FAU detection and automatic valence, arousal and (dis)liking intensity estimation.
We address the problem of speech enhancement generalisation to unseen environments by performing two manipulations. First, we embed an additional recording from the environment alone, and use this embedding to alter activations in the main enhancement subnetwork. Second, we scale the number of noise environments present at training time to 16,784 different environments. Experiment results show that both manipulations reduce word error rates of a pretrained speech recognition system and improve enhancement quality according to a number of performance measures. Specifically, our best model reduces the word error rate from 34.04% on noisy speech to 15.46% on the enhanced speech. Enhanced audio samples can be found in https://speechenhancement.page.link/samples.
Time-continuous emotion prediction has become an increasingly compelling task in machine learning. Considerable efforts have been made to advance the performance of these systems. Nonetheless, the main focus has been the development of more sophisticated models and the incorporation of different expressive modalities (e. g., speech, face, and physiology). In this paper, motivated by the benefit of difficulty awareness in a human learning procedure, we propose a novel machine learning framework, namely, Dynamic Difficulty Awareness Training (DDAT), which sheds fresh light on the research -- directly exploiting the difficulties in learning to boost the machine learning process. The DDAT framework consists of two stages: information retrieval and information exploitation. In the first stage, we make use of the reconstruction error of input features or the annotation uncertainty to estimate the difficulty of learning specific information. The obtained difficulty level is then used in tandem with original features to update the model input in a second learning stage with the expectation that the model can learn to focus on high difficulty regions of the learning process. We perform extensive experiments on a benchmark database (RECOLA) to evaluate the effectiveness of the proposed framework. The experimental results show that our approach outperforms related baselines as well as other well-established time-continuous emotion prediction systems, which suggests that dynamically integrating the difficulty information for neural networks can help enhance the learning process.
Over the past few years, adversarial training has become an extremely active research topic and has been successfully applied to various Artificial Intelligence (AI) domains. As a potentially crucial technique for the development of the next generation of emotional AI systems, we herein provide a comprehensive overview of the application of adversarial training to affective computing and sentiment analysis. Various representative adversarial training algorithms are explained and discussed accordingly, aimed at tackling diverse challenges associated with emotional AI systems. Further, we highlight a range of potential future research directions. We expect that this overview will help facilitate the development of adversarial training for affective computing and sentiment analysis in both the academic and industrial communities.
Acoustic Event Classification (AEC) has become a significant task for machines to perceive the surrounding auditory scene. However, extracting effective representations that capture the underlying characteristics of the acoustic events is still challenging. Previous methods mainly focused on designing the audio features in a 'hand-crafted' manner. Interestingly, data-learnt features have been recently reported to show better performance. Up to now, these were only considered on the frame-level. In this paper, we propose an unsupervised learning framework to learn a vector representation of an audio sequence for AEC. This framework consists of a Recurrent Neural Network (RNN) encoder and a RNN decoder, which respectively transforms the variable-length audio sequence into a fixed-length vector and reconstructs the input sequence on the generated vector. After training the encoder-decoder, we feed the audio sequences to the encoder and then take the learnt vectors as the audio sequence representations. Compared with previous methods, the proposed method can not only deal with the problem of arbitrary-lengths of audio streams, but also learn the salient information of the sequence. Extensive evaluation on a large-size acoustic event database is performed, and the empirical results demonstrate that the learnt audio sequence representation yields a significant performance improvement by a large margin compared with other state-of-the-art hand-crafted sequence features for AEC.
We develop a novel deep contour detection algorithm with a top-down fully convolutional encoder-decoder network. Our proposed method, named TD-CEDN, solves two important issues in this low-level vision problem: (1) learning multi-scale and multi-level features; and (2) applying an effective top-down refined approach in the networks. TD-CEDN performs the pixel-wise prediction by means of leveraging features at all layers of the net. Unlike skip connections and previous encoder-decoder methods, we first learn a coarse feature map after the encoder stage in a feedforward pass, and then refine this feature map in a top-down strategy during the decoder stage utilizing features at successively lower layers. Therefore, the deconvolutional process is conducted stepwise, which is guided by Deeply-Supervision Net providing the integrated direct supervision. The above proposed technologies lead to a more precise and clearer prediction. Our proposed algorithm achieved the state-of-the-art on the BSDS500 dataset (ODS F-score of 0.788), the PASCAL VOC2012 dataset (ODS F-score of 0.588), and and the NYU Depth dataset (ODS F-score of 0.735).
This paper presents a new approach to solving N-queen problems, which involves a model of distributed autonomous agents with artificial life (ALife) and a method of representing N-queen constraints in an agent environment. The distributed agents locally interact with their living environment, i.e., a chessboard, and execute their reactive behaviors by applying their behavioral rules for randomized motion, least-conflict position searching, and cooperating with other agents etc. The agent-based N-queen problem solving system evolves through selection and contest according to the rule of Survival of the Fittest, in which some agents will die or be eaten if their moving strategies are less efficient than others. The experimental results have shown that this system is capable of solving large-scale N-queen problems. This paper also provides a model of ALife agents for solving general CSPs.