Duration High-Order Hidden Markov Models and Training Algorithms for Speech Recognition

Improving Phoneme Sequence Recognition using Phoneme Duration Information in DNN-HSMM

Improving phoneme recognition has attracted the attention of many researchers due to its applications in various fields of speech processing. Recent research achievements show that using deep neural network (DNN) in speech recognition systems significantly improves the performance of these systems. There are two phases in DNN-based phoneme recognition systems including training and testing. Mos...

A Study of Duration High-Order Hidden Markov Models and Training Algorithms for Speech Recognition

The duration high-order hidden Markov model (DHO-HMM) can capture the dynamic evolution of a physical system more precisely than the first-order hidden Markov model (HMM). The relationship among DHO-HMM, high-order HMM (HO-HMM), hidden semi-Markov model (HSMM), and HMM is presented and discussed. We derived recursive forward and backward probability functions for the partial observation sequenc...

Speaker Independent Speech Recognition Using Hidden Markov Models for Persian Isolated Words

Speaker Independent Speech Recognition Using Hidden Markov Models for Persian Isolated Words

شبکه عصبی پیچشی با پنجره‌های قابل تطبیق برای بازشناسی گفتار

Although, speech recognition systems are widely used and their accuracies are continuously increased, there is a considerable performance gap between their accuracies and human recognition ability. This is partially due to high speaker variations in speech signal. Deep neural networks are among the best tools for acoustic modeling. Recently, using hybrid deep neural network and hidden Markov mo...