Here's a scientific look at computer-generated speech verification and identification -- its underlying technology, practical applications, and future direction. You get a solid background in voice recognition technology to help you make informed decisions on which voice recognition-based software to use in your company or organization. It is unique in its clear explanations of mathematical concepts, as well as its full-chapter presentation of the successful new Multi-Granular Segregating System for accurate, context-free speech identification.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Background of Voice Recognition
Methods of ContextFree Voice
6 other sections not shown
algorithm applications Automatic Speaker average filter compensation average vector bomb threat calculated centroid cepstral cepstral coefficients channel variation chapter codebook comparisons criterion value cross-validation cutoff Data flow described determined Dialect Region distance measures distortion scores error rate example exemplars experiment F-ratios feature extraction feature vectors forensic voice forensic voice-recognition formant formant frequencies function Hidden Markov Models HMMs ICASSP Impostor inverse filter ith component known speaker large number law enforcement LPC coefficients match method neural networks neuron normalized parameter space physical parameters pitch population problem Raw Scores recognition performance Recognition System recording rehumanizing filter technique sample secondary parameters segregating sequence similar sounds Speaker Identification Speaker Recognition Speaker Verification spectrogram spectrum speech recognition speech signal strategy suspect Table task Technology telephone test utterance Text-Independent Speaker th category TIMIT Database training and testing Type variance Vector Quantization vocal tract voice recognition voice-recognition systems voiceprint vowels weighted