Audio Mostly Conference 

Abstract: This paper investigates methods aiming at the automatic recognition and classification of discrete environmental sounds, for the purpose of subsequently applying these methods to the recognition of soundscapes. Research in audio recognition has traditionally focused on the domains of speech and music. Comparatively little research has been done towards recognizing non-speech environmental sounds. For this reason, in this paper, we apply existing techniques that have been proved efficient in the other two domains. These techniques are comprehensively compared to determine the most appropriate one for addressing the problem of environmental sound recognition.

Abstract: In this work, a novel representation system for symbolic music is described. The proposed representation system is graph-based and could theoretically represent music both from a horizontal (contrapuntal) and from a vertical (harmonic) point of view, by keeping into account contextual and harmonic information. It could also include relationships between internal variations of motifs and themes. This is achieved by gradually simplifying the melodies and generating layers of reductions that include only the most important notes from a structural and harmonic viewpoint. This representation system has been tested in a music information retrieval task, namely melodic similarity, and compared to another system that performs the same task but does not consider any contextual or harmonic information, showing how the structural information is needed in order to find certain relations between musical pieces. Moreover, a new dataset consisting of more than 5000 leadsheets is presented, with additional meta-musical information taken from different web databases, including author, year of first performance, lyrics, genre and stylistic tags.

Abstract: This paper presents an experiment testing which sound parameters, in a survival horror game context, most warrant further investigation as a means to control the level of fear in such games. The experiment is part of a long-term study ultimately designed to support the development of a biofeedback procedural audio engine for computer games. By this means, it is hoped to provide an enhanced gaming experience whereby sound synthesis and audio processing is conducted in real-time according to the player's affect responses and emotional state. Results indicate that coarse manipulation of audio parameters has the potential to influence the intensity of the player's fear response whilst playing a survival horror game. Evidence is also presented that supports the integration of event logging and realtime participant vocal response into an experimental design to gather unbiased, quantitative data that can be associated with qualitative emotional response.

Abstract: In this paper, we investigate a previously proposed algorithm for spoken language identification based on convolutional neural networks and convolutional recurrent neural networks. We improve the algorithm by modifying the training strategy to ensure equal class distribution and efficient memory usage. We successfully replicate previous experimental findings using a modified set of languages. Our findings confirm that both a convolutional neural network as well as convolutional recurrent neural networks are capable to learn language-specific patterns in mel spectrogram representations of speech recordings.