Speech Models Training Technologies Comparison Using Word Error Rate

Abstract

The main purpose of this work is to analyze and compare several technologies used for training speech models, including traditional approaches as Hidden Markov Models (HMMs) and more recent methods as Deep Neural Networks (DNNs). The technologies have been explained and compared using word error rate metric based on the input of 1000 words by a user with 15 decibel background noise. Word error rate metric has been explained and calculated. Potential replacements for compared technologies have been provided, including: Attention-based, Generative, Sparse and Quantum-inspired models. Pros and cons of those techniques as a potential replacement have been analyzed and listed. Data analyzing tools and methods have been explained and most common datasets used for HMM and DNN technologies have been described. Real life usage examples of both methods have been provided and systems based on them have been analyzed.