TDNNs used to solve problems in speech recognition that were introduced in 19871989<ref name=":0" /> and initially focused on shift-invariant phoneme recognition. Speech lends itself nicely to TDNNs as spoken sounds are rarely of uniform length and precise segmentation is difficult or impossible. By scanning a sound over past and future, the TDNN is able to construct a model for the key elements of that sound in a time-shift invariant manner. This is particularly useful as sounds are smeared out through reverberation.<ref name=":4" /><ref name=":5" /> Large phonetic TDNNs can be constructed modularly through pre-training and combining smaller networks.<ref name=":3" />
