Time delay neural network: Difference between revisions

Revision as of 07:43, 30 June 2019

Revision as of 10:11, 30 June 2019

Line 10:

The TDNN was first proposed to classify [[phonemes]] in speech signals for automatic [[speech recognition]], where the automatic determination of precise segments or feature boundaries is difficult or impossible. Because the TDNN recognizes phonemes and their underlying acoustic/phonetic features, independent of position in time, it improved performance over static classification.<ref name="phoneme detection" /><ref name=":0">Alexander Waibel, ''Phoneme Recognition Using Time-Delay Neural Networks'', SP87-100, Meeting of the Institute of Electrical, Information and Communication Engineers (IEICE), December, 1987,Tokyo, Japan.</ref> It was also applied to two-dimensional signals (time-frequency patterns in speech,<ref name=":1">John B. Hampshire and Alexander Waibel, ''Connectionist Architectures for Multi-Speaker Phoneme Recognition'', Advances in Neural Information Processing Systems, 1990, Morgan Kaufmann.</ref> and coordinate space pattern in OCR<ref name=":2">Stefan Jaeger, Stefan Manke, Juergen Reichert, Alexander Waibel, ''Online handwriting recognition: the NPen++recognizer'', International Journal on Document Analysis and Recognition Vol. 3, Issue 3, March 2001</ref>).

==== Max pooling ====

In 1990 Yamaguchi et al. introduced the concept of max pooling. They did so by combining TDNNs with max pooling in order to realize a speaker independent isolated word recognition system.<ref name="Yamaguchi111990">{{cite conference |title=A Neural Network for Speaker-Independent Isolated Word Recognition |last1=Yamaguchi |first1=Kouichi |last2=Sakamoto |first2=Kenji |last3=Akabane |first3=Toshio |last4=Fujimoto |first4=Yoshiji |date=November 1990 |___location=Kobe, Japan |conference=First International Conference on Spoken Language Processing (ICSLP 90)}}</ref>

==Overview==