Preliminary results on speaker-independant speech recognition are reported. A method that combines expertise on neural networks with expertise on speech recognition is used to build the recognition systems. For transient sounds, event-driven property extractors with variable resolution in the time and frequency domains are used. For sonorant speech, a model of the human auditory system is preferred to FFT as a front-end module.
Use of Multi-Layered Networks for Coding Speech with Phonetic Features
Contributo in volume
MORGAN KAUFMANN, Palo Alto, USA
Advances in Neural Information Processing Systems, edited by D.S. Touretzky, pp. 224–231. Palo Alto: MORGAN KAUFMANN, 1989