BEADS: A dataset of Binaural Emotionally Annotated Digital Sounds

2017 Seventh International Conference on Affective Computing and Intelligent Interaction (ACII), 2017

Soundscape emotion recognition (SER) aims at the automatic recognition of emotions perceived in soundscape recordings. To benchmark SER, we propose a dataset of audio samples called Emo-Soundscapes and two evaluation protocols for machine learning models. We curated 600 soundscape recordings from Freesound.org and mixed 613 audio clips from a combination of these. The Emo-Soundscapes dataset contains 1213 6-second Creative Commons licensed audio clips. We collected the ground truth annotations of perceived emotion in these 1213 soundscape recordings using a crowdsourcing listening experiment, where 1182 annotators from 74 different countries rank the audio clips according to the perceived valence and arousal. This dataset allows studying SER and how the mixing of various soundscape recordings influences their perceived emotion. The dataset is at http://metacreation.net/emo-soundscapes/.

AM '12 Proceedings of the 7th Audio Mostly Conference: A Conference on Interaction with Sound

Sound events can carry multiple information, related to the sound source and to ambient environment. However, it is well-known that sound evokes emotions, a fact that is verified by works in the disciplines of Music Emotion Recognition and Music Information Retrieval that focused on the impact of music to emotions. In this work we introduce the concept of affective acoustic ecology that extends the above relation to the general concept of sound events. Towards this aim, we define sound event as a novel audio structure with multiple components. We further investigate the application of existing emotion models employed for music affective analysis to sonic, non-musical, content. The obtained results indicate that although such application is feasible, no significant trends and classification outcomes are observed that would allow the definition of an analytic relation between the technical characteristics of a sound event waveform and raised emotions.

Electronics, 2021

A frequently used procedure to examine the relationship between categorical and dimensional descriptions of emotions is to ask subjects to place verbal expressions representing emotions in a continuous multidimensional emotional space. This work chooses a different approach. It aims at creating a system predicting the values of Activation and Valence (AV) directly from the sound of emotional speech utterances without the use of its semantic content or any other additional information. The system uses X-vectors to represent sound characteristics of the utterance and Support Vector Regressor for the estimation the AV values. The system is trained on a pool of three publicly available databases with dimensional annotation of emotions. The quality of regression is evaluated on the test sets of the same databases. Mapping of categorical emotions to the dimensional space is tested on another pool of eight categorically annotated databases. The aim of the work was to test whether in each u...

2011

In this article, we propose a new set of acoustic features for automatic emotion recognition from audio. The features are based on the perceptual quality metrics that are given in perceptual evaluation of audio quality known as ITU BS.1387 recommendation. Starting from the outer and middle ear models of the auditory system, we base our features on the masked perceptual loudness which defines relatively objective criteria for emotion detection. The features computed in critical bands based on the reference concept include the partial loudness of the emotional difference, emotional difference-to-perceptual mask ratio, measures of alterations of temporal envelopes, measures of harmonics of the emotional difference, the occurrence probability of emotional blocks, and perceptual bandwidth. A soft-majority voting decision rule that strengthens the conventional majority voting is proposed to assess the classifier outputs. Compared to the state-of-the-art systems including Munich Open-Source Emotion and Affect Recognition Toolkit, Hidden Markov Toolkit, and Generalized Discriminant Analysis, it is shown that the emotion recognition rates are improved between 7-16% for EMO-DB and 7-11% in VAM for "all" and "valence" tasks.

TheAudio/VisualEmotionChallengeandWorkshop(AVEC 2011) is the first competition event aimed at comparison of multimedia processing and machine learning methods for automatic audio, visual and audiovisual emotion analysis, with all participants competing under strictly the same conditions. This paper first describes the challenge par- ticipation conditions. Next follows the data used – the SEMAINE corpus – and its partitioning into train, development, and test partitions for the challenge with labelling in four dimensions, namely activity, expectation, power, and valence. Further, audio and video baseline features are intro- duced as well as baseline results that use these features for the three sub-challenges of audio, video, and audiovisual emotion recognition.

Behavior Research Methods, 2014

The purpose of this study was to develop an auditory emotion recognition function that could determine the emotion caused by sounds coming from the environment in our daily life. For this purpose, sound stimuli from the International Affective Digitized Sounds (IADS-2), a standardized database of sounds intended to evoke emotion, were selected, and four psychoacoustic parameters (i.e., loudness, sharpness, roughness, and fluctuation strength) were extracted from the sounds. Also, by using an emotion adjective scale, 140 college students were tested to measure three basic emotions (happiness, sadness, and negativity). From this discriminant analysis to predict basic emotions from the psychoacoustic parameters of sound, a discriminant function with overall discriminant accuracy of 88.9 % was produced from training data. In order to validate the discriminant function, the same four psychoacoustic parameters were extracted from 46 sound stimuli collected from another database and substituted into the discriminant function. The results showed that an overall discriminant accuracy of 63.04 % was confirmed. Our findings provide the possibility that daily-life sounds, beyond voice and music, can be used in a human-machine interface.

2016

Sound events are proven to have an impact on the emotions of the listener. Recent works on the field of emotion recognition from sound events show, on one hand, the possibility of automatic emotional information retrieval from sound events and, on the other hand, the need for deeper understanding of the significance of the sound events’ semantic content on listener’s affective state. In this work we present a first, to the best of authors’ knowledge, investigation of the relation between the semantic similarity of the sound events and the elicited emotion. For that cause we use two emotionally annotated sound datasets and the Wu-Palmer semantic similarity measure according to WordNet. Results indicate that the semantic content seems to have a limited role in the conformation of the listener’s affective states. On the contrary, when the semantic content is matched to specific areas in the Arousal - Valence space or also the source’s spatial position is taken into account, it is exhibited that the importance of the semantic content effect is higher, especially for the cases with medium to low valence and medium to high arousal or when the sound source is at the lateral positions of the listener’s head, respectively.

Journal of the Audio Engineering Society, 2016

Soundscape affect recognition is essential for sound designers and soundscape composers. Previous work demonstrated the effectiveness of predicting valence and arousal of soundscapes in responses from one expert user. Based on this, we present a method for the automatic soundscape affect recognition using ground truth data collected from an online survey. An analysis of the corpus shows that participants have a high level of agreement on the valence and arousal of soundscapes. We generate a gold standard by averaging users' responses, and we verify the corpus by training stepwise linear regression models and support vector regression models. An analysis of the models shows our system obtains better results than the previous study. Further, we test the correlation between valence and arousal based on the gold standard. Last, we report an experiment of using arousal as a feature for predicting valence and vice versa.

Journal of the Acoustical …, 2008

Research regarding the perception of sound focuses in large on the acoustical properties of the sound. We argue that, for a more complete picture of sound perception, one must take the non-physical properties into account. By changing the emotional descriptor of a sound the perception in terms of level of annoyance will change. The present study investigates how a priming picture placing the origin of the sound to either a positive or negative environment affects the level of annoyance to same sound. 3 different sounds were used in the experiment, all based on pink noise. The participants were in the beginning of each sound exposed to a picture telling where the sound originated. The picture was either a positive environment (a picture of a waterfall) or a negative environment (a picture of a larger factory). While listening to the sounds the participants completed different performance tasks. In the end of each sound the participants rated level of annoyance to the sound. Results show that the annoyance ratings are significantly lower when primed with a positive picture. Results also indicate that for more attention demanding tasks this correlation is stronger. The findings are discussed in relation to theories of sound perception.

2009

Abstract Most emotion recognition systems still rely exclusively on prototypical emotional vocal expressions that may be uniquely assigned to a particular class. In realistic applications, there is, however, no guarantee that emotions are expressed in a prototypical manner. In this paper, we report on challenges that arise when coping with non-prototypical emotions in the context of the CALLAS project and the IRIS network.