Towards Audio-Visual Navigation in Noisy Environments: A Large-Scale Benchmark Dataset and an Architecture Considering Multiple Sound-Sources

Audio-visual navigation has received considerable attention in recent years. However, the majority of related investigations have focused on single sound-source scenarios. Studies in this field for multiple sound-source scenarios remain underexplored due to the limitations of two aspects. First, the existing audio-visual navigation dataset only has limited audio samples, making it difficult to simulate diverse multiple sound-source environments. Second, existing navigation frameworks are mainly designed for single sound-source scenarios, thus their performance is severely reduced in multiple sound-source scenarios. In this work, we make an attempt to fill in these two research gaps to some extent. First, we establish a large-scale BEnchmark Dataset for Audio-VIsual Navigation, namely BeDAViN. This dataset consists of 2,258 audio samples with a total duration of 10.8 hours, which is more than 33 times longer than the existing audio dataset employed in the audio-visual navigation task. Second, we propose a new Embodied Navigation framework for MUltiple Sound-Sources Scenarios called ENMuS 3 . There are mainly two essential components in ENMuS 3 , the sound event descriptor and the multi-scale scene memory transformer. The former component equips the agent with the ability to extract spatial and semantic features of the target sound-source among multiple sound-sources, while the latter provides the ability to track the target object effectively in noisy environments. Experimental results on our BeDAViN show that ENMuS 3 strongly outperforms its counterparts with an orderof-magnitude improvement in success rates across diverse scenarios.