Title :
High-performance low-complexity wordspotting using neural networks
Author :
Chang, Eric I. ; Lippmann, Richard P.
Author_Institution :
Nuance Commun., Menlo Park, CA, USA
fDate :
11/1/1997 12:00:00 AM
Abstract :
A high-performance low-complexity neural network wordspotter was developed using radial basis function (RBF) neutral networks in a hidden Markov model (HMM) framework. Two new complementary approaches substantially improve performance on the talker-independent Switchboard corpus. Figure of merit (FOM) training adapts wordspotter parameters to directly improve the FOM performance metric, and voice transformations generate additional training examples by warping the spectra of training data to mimic across-talker vocal tract length variability
Keywords :
feedforward neural nets; hidden Markov models; learning (artificial intelligence); speech processing; speech recognition; FOM performance metric; HMM; across-talker vocal tract length variability; figure of merit training; hidden Markov model; high performance wordspotting; low complexity wordspotting; neural network wordspotter; radial basis function networks; spectra warping; talker-independent Switchboard corpus; training data; voice transformations; wordspotter parameters; Acoustic signal detection; Control systems; Hidden Markov models; Maximum likelihood detection; Measurement; NIST; Neural networks; Speech; Testing; Training data;
Journal_Title :
Signal Processing, IEEE Transactions on
