What people are saying - Write a review
We haven't found any reviews in the usual places.
Speech Production and Synthesis
49 other sections not shown
Other editions - View all
acoustic models across-word models Adaptive allophonic Analysis Applications approach Audio baseline beam search bigram CDHMM CDMA cepstral Channel classification codebook Coding coefficients computation context continuous speech recognition correlation database decision tree decision-tree densities Digital discriminative distribution DMHMMs efficient Estimation evaluation experiments fast Figure Filter forward-backward frame frequency function Gaussian mixture Hidden Markov Models hypotheses IEEE Image improved input language model large vocabulary lattice lexical likelihood linear masking threshold MBSD measure method MFCCs multi-resolution MVDR n-best n-gram node noise masking threshold obtained optimal paper parameters path performance phonetic probability problem Proc procedure proposed pruning quantization recognition accuracy recognizer rescoring Robust samples score sentences sequence Serbo-Croatian Signal Processing speaker spectral subvectors Support Vector Machines SVMs syllable Table task technique tion topic-words training data transcriptions Transform triphones utterances vector vector quantization Viterbi Viterbi algorithm vowel word error rate word graph