@article{Schuller_Amiriparian_Keren_Baird_Schmitt_Cummins_2020, title={The next generation of audio intelligence: A survey-based perspective on improving audio analysis}, volume={7}, url={https://proceedings.isaar.eu/index.php/isaarproc/article/view/2019-13}, abstractNote={<div class="page" title="Page 1"> <div class="layoutArea"> <div class="column"> <p>Computer audition has made major progress over the past decades; however it is still far from achieving human-level hearing abilities. Imagine, for example, the sounds associated with putting a water glass onto a table. As humans, we would be able to roughly “hear” the material of the glass, the table, and perhaps even how full the glass is. Current machine listening approaches, on the other hand, would mainly recognise the event of “glass put onto a table”. In this context, this contribution aims to provide key insight into the already made remarkable advances in computer audition. It also identifies deficits in reaching human-like hearing abilities, such as in the given example. We summarise the state-of-the-art in traditional signal-processing-based audio pre-processing and feature representation, as well as automated learning such as by deep neural networks. This concerns, in particular, audio diarisation, source separation, understanding, but also ontologisation. Based on this, concluding avenues are given towards reaching the ambitious goal of “holistic human-parity” machine listening abilities – the next generation of audio intelligence.</p> </div> </div> </div>}, journal={Proceedings of the International Symposium on Auditory and Audiological Research}, author={Schuller, Björn and Amiriparian, Shahin and Keren, Gil and Baird, Alice and Schmitt, Maximilian and Cummins, Nicholas}, year={2020}, month={Apr.}, pages={101–112} }