We used deep convolutional networks on spectrograms for a spoken language identification task. We had around 95% accuracy on a dataset provided in this TopCoder contest. The details are here.
Plain convolutional networks do not capture the temporal characteristics, so for example in this work the output of the convolutional network was fed to a time-delay neural network. But our experiments show that even without additional elements convolutional networks can perform well at least on some tasks when the inputs have similar sizes.