Towards Constructing HMM Structure for Speech Recognition With Deep Neural Fenonic Baseform Growing

Towards Constructing HMM Structure for Speech Recognition With Deep Neural Fenonic Baseform Growing

For decades, acoustic models in speech recognition systems pivot on Hidden Markov Models (HMMs), e.g., Gaussian Mixture Model-HMM system, Deep Neural Network-HMM system, etc., and achieve remarkable results. However, the popular HMM model is the three-state left-to-right structure, without the super...

Full description

Bibliographic Details
Main Authors: Lujun Li, Tobias Watzel, Ludwig Kurzinger, Gerhard Rigoll
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Deep neural network
HMM topology
speech recognition
vector quantization
Online Access:https://ieeexplore.ieee.org/document/9371697/

Internet

https://ieeexplore.ieee.org/document/9371697/

Similar Items