🚀 go-pugleaf

CS COLLOQUIUM

Neural Network Speech Processing
For Toys and Consumer Electronics

Michael C. Mozer
University of Colorado, Boulder and
Sensory Circuits, Inc.

October 3, 1996
3:45 - 4:45 pm
Engineering Center Classroom 265

Refreshments will be served at 3:30 pm

The ongoing challenge in speech research is recognizing continuous,
unconstrained speech.  In comparison, isolated word recognition with small
vocabularies is easy.  Many commercial efforts are aimed at the high-end
problem.  Sensory Circuits has successfully focused on the low end,
producing a family of low-cost speech recognition chips for toys, consumer
electronics,
electronic learning aids, and home appliances.  The chips are based on a 4
MIPS 8-bit microcontroller with on board AGC, A/D, D/A, and digital
filtering.  The microcontroller can be programmed for speaker-independent
or dependent recognition, voice verification (recognizing a stored password
spoken by particular speaker), polyphonic music synthesis, speech
synthesis,
voice record and playback, and has enough power to drive and communicate
with the application product.  The speech recognition and voice
verification products are neural-network based.  Speaker-independent
recognition of up-to-10 word vocabularies achieves accuracies of 95-98%.
Speaker-dependent recognition of vocabularies of up-to-20 items has an
accuracy greater than
99%.  The chip can be programmed to handle larger vocabularies by
context-dependent switching of recognition sets.  The neural net
architectures are fairly standard, but the hardware and real-world usage
impose some interesting challenges, including speed constraints which
necessitate integer arithmetic, very limited RAM, and on-line speaker
adaptation.  I will demo
various products with neural network speech recognition.

Host:  Dirk Grunwald
------------------------------
http://www.cs.colorado.edu/~grunwald/Colloquia.html



***********************************
Pat Libhart
Department of Computer Science
University of Colorado
Campus Box 430, ECOT 717
Boulder, CO  80309-0430
Phone:  (303)492-7514
Fax:  (303)492-2844
e-mail:  libhart@cs.colorado.edu
***********************************