This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
|
||||||||
|
Paper Details
Paper Title
Introduction to Various Algorithms of Speech Recognition: Hidden Markov Model, Dynamic Time Warping and Artificial Neural Networks
Authors
  Pahini A. Trivedi
Abstract
Abstract-Now a day’s speech recognition is used widely in many applications. In computer science and electrical engineering, speech recognition (SR) is the translation of spoken words into text. It is also known as "automatic speech recognition" (ASR), "computer speech recognition", or just "speech to text" (STT). A hidden Markov model (HMM) is a statistical Markov model in which the system being modelled is assumed to be a Markov process with unobserved (hidden) states. An HMM can be presented as the simplest dynamic Bayesian network. Dynamic time warping (DTW) is a well-known technique to find an optimal alignment between two given (time-dependent) sequences under certain restrictions intuitively; the sequences are warped in a nonlinear fashion to match each other. ANN is non-linear data driven self-adaptive approach. It can identify and learn co-related patterns between input dataset and corresponding target values. After training ANN can be used to predict the outcome of new independent input data.
Keywords- Index Terms -SR, HMM, DTW, ANN
Publication Details
Unique Identification Number - IJEDR1404035Page Number(s) - 3590-3596Pubished in - Volume 2 | Issue 4 | Dec 2014DOI (Digital Object Identifier) -    --Publisher - IJEDR (ISSN - 2321-9939)
Cite this Article
  Pahini A. Trivedi,   "Introduction to Various Algorithms of Speech Recognition: Hidden Markov Model, Dynamic Time Warping and Artificial Neural Networks", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.2, Issue 4, pp.3590-3596, Dec 2014, Available at :http://www.ijedr.org/papers/IJEDR1404035.pdf
Article Preview
|
|
||||||
|