Speech Processing and Soft Computing
Springer Science & Business Media, Sep 2, 2011 - Technology & Engineering - 104 pages
Speech Processing and Soft Computing includes coverage of synergy between speech technology and bio-inspired soft computing methods. Through practical cases, the author explores, dissects and examines how soft computing may complement conventional techniques in speech enhancement and speech recognition in order to provide robust systems. The material is especially useful to graduate students and experienced researchers who are interested in expanding their horizons and investigating new research directions through review of the theoretical and practical settings of soft computing methods in very recent speech applications.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Other editions - View all
acoustic adaptation data adaptation technique applied approach AR-TDNN ASR robustness ASR systems auditory autoregressive cepstral cepstral coefficients cepstrum channel Chapter clean signal clean speech consists criterion crossover cues database dialog manager discriminative distortion domain eigenvalues energy enhancement methods environment Equation evaluation evolutionary evolutionary-based fittest individual frequency front-end Gaussian genetic algorithms genetic operators Hidden Markov Models HMMs hybrid improve input language model linear transforms matrix measures MFCCs mismatch MLLR mutation nasal vowels neural networks noise reduction noise subspace noisy signal noisy speech objective function obtained optimal output parameters perceptual performance PESQ population principal components Processing and Soft proposed reconstruction error selection Selouani sequence signal subspace Singular Value Decomposition soft computing soft computing techniques solution speaker adaptation spectrum Speech Processing speech quality speech recognition system speech signal Springer Science+Business Media SpringerBriefs in Electrical subspace decomposition subspace filtering TIMIT values weights