Kebe, G. Y., L. E. Richards, E. Raff, F. Ferraro, and C. Matuszek. “Bridging the Gap: Using Deep Acoustic Representations to Learn Grounded Language from Percepts and Raw Speech”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 10, June 2022, pp. 10884-93, doi:10.1609/aaai.v36i10.21335.