Recent advances in transformer-based architectures which are pre-trained in self-supervised manner have shown great promise in several machine learning tasks. In the audio domain, such architectures have also been successfully utilised in the field of speech emotion recognition (SER). However, existing works have not evaluated the influence of model size and pre-training data on downstream performance, and have shown limited attention to generalisation, robustness, fairness, and efficiency. The present contribution conducts a thorough analysis of these aspects on several pre-trained variants of wav2vec 2.0 and HuBERT that we fine-tuned on the dimensions arousal, dominance, and valence of MSP-Podcast, while additionally using IEMOCAP and MOSI to test cross-corpus generalisation. To the best of our knowledge, we obtain the top performance for valence prediction without use of explicit linguistic information, with a concordance correlation coefficient (CCC) of .638 on MSP-Podcast. Furthermore, our investigations reveal that transformer-based architectures are more robust to small perturbations compared to a CNN-based baseline and fair with respect to biological sex groups, but not towards individual speakers. Finally, we are the first to show that their extraordinary success on valence is based on implicit linguistic information learnt during fine-tuning of the transformer layers, which explains why they perform on-par with recent multimodal approaches that explicitly utilise textual information. Our findings collectively paint the following picture: transformer-based architectures constitute the new state-of-the-art in SER, but further advances are needed to mitigate remaining robustness and individual speaker issues. To make our findings reproducible, we release the best performing model to the community.

Large, pre-trained neural networks consisting of self-attention layers (transformers) have recently achieved state-of-the-art results on several speech emotion recognition (SER) datasets. These models are typically pre-trained in self-supervised manner with the goal to improve automatic speech recognition performance -- and thus, to understand linguistic information. In this work, we investigate the extent in which this information is exploited during SER fine-tuning. Using a reproducible methodology based on open-source tools, we synthesise prosodically neutral speech utterances while varying the sentiment of the text. Valence predictions of the transformer model are very reactive to positive and negative sentiment content, as well as negations, but not to intensifiers or reducers, while none of those linguistic features impact arousal or dominance. These findings show that transformers can successfully leverage linguistic information to improve their valence predictions, and that linguistic analysis should be included in their testing.

The Audio/Visual Emotion Challenge and Workshop (AVEC 2019) "State-of-Mind, Detecting Depression with AI, and Cross-cultural Affect Recognition" is the ninth competition event aimed at the comparison of multimedia processing and machine learning methods for automatic audiovisual health and emotion analysis, with all participants competing strictly under the same conditions. The goal of the Challenge is to provide a common benchmark test set for multimodal information processing and to bring together the health and emotion recognition communities, as well as the audiovisual processing communities, to compare the relative merits of various approaches to health and emotion recognition from real-life data. This paper presents the major novelties introduced this year, the challenge guidelines, the data used, and the performance of the baseline systems on the three proposed tasks: state-of-mind recognition, depression assessment with AI, and cross-cultural affect sensing, respectively.

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 consider the task of weakly supervised one-shot detection. In this task, we attempt to perform a detection task over a set of unseen classes, when training only using weak binary labels that indicate the existence of a class instance in a given example. The model is conditioned on a single exemplar of an unseen class and a target example that may or may not contain an instance of the same class as the exemplar. A similarity map is computed by using a Siamese neural network to map the exemplar and regions of the target example to a latent representation space and then computing cosine similarity scores between representations. An attention mechanism weights different regions in the target example, and enables learning of the one-shot detection task using the weaker labels alone. The model can be applied to detection tasks from different domains, including computer vision object detection. We evaluate our attention Siamese networks on a one-shot detection task from the audio domain, where it detects audio keywords in spoken utterances. Our model considerably outperforms a baseline approach and yields a 42.6% average precision for detection across 10 unseen classes. Moreover, architectural developments from computer vision object detection models such as a region proposal network can be incorporated into the model architecture, and results show that performance is expected to improve by doing so.