Humans can robustly recognize and localize objects by integrating visual and auditory cues. While machines are able to do the same now with images, less work has been done with sounds. This work develops an approach for dense semantic labelling of sound-making objects, purely based on binaural sounds. We propose a novel sensor setup and record a new audio-visual dataset of street scenes with eight professional binaural microphones and a 360 degree camera. The co-existence of visual and audio cues is leveraged for supervision transfer. In particular, we employ a cross-modal distillation framework that consists of a vision `teacher' method and a sound `student' method -- the student method is trained to generate the same results as the teacher method. This way, the auditory system can be trained without using human annotations. We also propose two auxiliary tasks namely, a) a novel task on Spatial Sound Super-resolution to increase the spatial resolution of sounds, and b) dense depth prediction of the scene. We then formulate the three tasks into one end-to-end trainable multi-tasking network aiming to boost the overall performance. Experimental results on the dataset show that 1) our method achieves promising results for semantic prediction and the two auxiliary tasks; and 2) the three tasks are mutually beneficial -- training them together achieves the best performance and 3) the number and orientations of microphones are both important. The data and code will be released to facilitate the research in this new direction.