Next: The Geometrical Processing Up: Projects Previous: Study of Machine

Study on Speech Recognition under Noisy Environment

Masahide Sugiyama,
Professor, Human Interface Laboratory

FPM-LR neural-network speaker-independent continuous speech recognition system has been implemented on SUN/SS10 and HP9000/755 workstations. We have also developed a distance-sensitive microphone system. In the following project we will evaluate the effectiveness of the new microphone system in speech recognition performance. We purchased ESPS and HTK (HMM Tool Kit). We will also evaluate the effectiveness the composition technique of noise and speech and the new microphone system in recognition performance.
Fri Feb 10 09:19:38 JST 1995