KIAM Main page Web Library  •  Publication Searh  Русский 

KIAM Preprint № 87, Moscow, 2001
Authors: Bayakovsky Yu.M., Zhirkov A.O., Kortchagine D.N., Krylov A.S., Lukin A.S.
Ann Based Analysis and Comparison of Time-Frequency Feature Vectors Based on Short Time Spectral Representation and Adaptive Hermite Transform.
The method of speech recognition based on representation of speech information by 2D time frequency feature vectors stream is considered. These vectors are constructed from the time-frequency information using 2D-wavelet transform of spectrogram image. Classification of vectors is processed by ANN. Sonograms of short time Fourier transform and adaptive Hermite transform form are the input speech information. These representations are compared for tasks of speaker-independent speech recognition and speech-independent speaker recognition.
Publication language: russian
Research direction:
Programming, parallel computing, multimedia
Russian source text:
View statistics (updated once a day)
over the last 30 days — 4 (-8), total hit from 01.09.2019 — 161