Can I read Speech Recognition: Feature Extraction & HMMs on EtoBox?

Speech Recognition: Feature Extraction & HMMs by Dewayu Dewi is a document available to read on EtoBox.

What is Speech Recognition: Feature Extraction & HMMs about?

This document provides an overview and outline of topics to be covered in a lecture on feature extraction and acoustic modeling for speech recognition. The lecture will cover Mel-frequency cepstral coefficients (MFCCs) as the most widely used spectral representation, and increasingly sophisticated acoustic models including Gaussian mixtures as the acoustic likelihood for each hidden Markov model state. Evaluation of speech recognition systems is discussed briefly in terms of word error rate.

Author

Dewayu Dewi

Language

EN