Time delay neural network: Difference between revisions

Revision as of 18:31, 10 March 2019

Revision as of 18:31, 10 March 2019

Line 34:

=== Speech recognition ===

TDNNs used to solve problems in speech recognition that were introduced in 1987 <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 TDNN’sTDNNs can be constructed modularly through pre-training and combining smaller networks.<ref name=":3" />

=== Large vocabulary speech recognition ===

Line 42:

=== Speaker independence ===

Two-dimensional variants of the TDNN’sTDNNs were proposed for speaker independence.<ref name=":1" /> Here, shift-invariance is applied to the time ''as well as'' to the frequency axis in order to learn hidden features that are independent of precise ___location in time and in frequency (the latter being due to speaker variability).

=== Reverberation ===