NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:8140
Title:Untangling in Invariant Speech Recognition

The authors propose to borrow some recently developed statistical mechanical theory, and apply it to neural networks in the context of speech recognition, to study hidden representations. As noted by the reviewers, findings are already known - the novelty lies more into the application of the theory to ASR. The idea could be possibly extended to other applications in future work.