Acoustic Model Training, using Kaldi, for Automatic Whispery Speech Recognition
Journal Title: Annals of Computer Science and Information Systems - Year 2018, Vol 16, Issue
Abstract
The article presents research on the automatic whispery speech recognition. The main task was to find dependences between a number of triphone classes (number of leaves in decision tree) and the total number of Gaussian distributions and therefore, to determine optimal values, for which the quality of speech recognition is best. Moreover, it was found, how these dependences differ between normal and whispery speech, what was not done earlier, and this is the innovative part of this work. Based on the performed experiments and obtained results one can say that the number of triphone classes (number of leaves) for whispered speech should be significantly lower than for normal speech.
Authors and Affiliations
Piotr Kozierski, Talar Sadalla, Szymon Drgas, Adam Dąbrowski, Joanna Ziętkiewicz, Wojciech Giernacki
Keywords
Related Articles
- EP ID EP568223
- DOI 10.15439/2018F255
- Views 47
- Downloads 0
Towards a Supportive City with Smart Urban Objects in the Internet of Things: The Case of Adaptive Park Bench and Adaptive Light
Internet of things technology is a key driver to build smart city infrastructure. The potentials for urban management problems which require process control and allocation mechanisms has long been acknowledged. However,...
Design of Intelligent PD Controller for Water Supply in Healthcare Systems
The necessity of clean environment is the major aspect in this modern age. This maintains a healthy environment. Also several trials have made with multidisciplinary researchers for development of healthy environment. Ho...
Deep Evolving Stacking Convex Cascade Neo-Fuzzy Network and Its Rapid Learning
A deep evolving stacking convex neo-fuzzy network is proposed. It is a feedforward cascade hybrid system, the layers-stacks of which are formed by generalized neo-fuzzy neurons that implement Wang--Mendel fuzzy reasoning...
Challenges in Causal Inference from Personal Monitoring Devices
Personal Monitoring Devices (PMDs) collect im- mense amount of data about health and wellness of hundreds of millions of people. One of the obstacles of the prevailing data analytics approaches to PMDs' data is limited v...
A Chatbot Based On AIML Rules Extracted From Twitter Dialogues
A chat dialogue system, a chatbot, or a conversational agent is a computer program designed to hold a conversation using natural language. Many popular chat dialogue systems are based on handcrafted rules, written in Art...