Neural Associative Memories and Hidden Markov Models for Speech Recognition

We have implemented a system that can understand spoken command sentences like "Bot lift green apple" using hidden Markov models (HMMs) and neural associative memories. After speaking a command sentence into a microphone, the system processes it in three stages: As first step, the auditory input is transformed into a convenient subsymbolic representation (diphones or triphones) using HMMs. The second step retrieves a symbolic representation (words) from the subsymbolic representation using a network of neural associative memories. Finally, in step three a semantic representation is obtained using neural associative memories. Furthermore, the system can learn new object words during performance.

[1]  Franz J. Kurfess,et al.  Information storage capacity of incompletely connected associative memories , 1998, Neural Networks.

[2]  Günther Palm,et al.  Combining Visual Attention, Object Recognition and Associative Information Processing in a NeuroBotic System , 2005, Biomimetic Neural Learning for Intelligent Robots.

[3]  James H. Martin,et al.  Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition, 2nd Edition , 2000, Prentice Hall series in artificial intelligence.

[4]  Günther Palm,et al.  Iterative retrieval of sparsely coded associative memory patterns , 1996, Neural Networks.

[5]  Jonathan G. Fiscus,et al.  Darpa Timit Acoustic-Phonetic Continuous Speech Corpus CD-ROM {TIMIT} | NIST , 1993 .

[6]  Andreas Knoblauch,et al.  Pattern separation and synchronization in spiking associative memories and visual areas , 2001, Neural Networks.

[7]  G. Palm,et al.  On associative memory , 2004, Biological Cybernetics.

[8]  David Willshaw,et al.  Capacity and information efficiency of the associative net , 1997 .

[9]  H. C. LONGUET-HIGGINS,et al.  Non-Holographic Associative Memory , 1969, Nature.

[10]  Biing-Hwang Juang,et al.  Fundamentals of speech recognition , 1993, Prentice Hall signal processing series.

[11]  Günther Palm,et al.  Detecting Sequences and Understanding Language with Neural Associative Memories and Cell Assemblies , 2005, Biomimetic Neural Learning for Intelligent Robots.