Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Improving performance of a GSM-based speech recognizer
[page 73 missing] Communication between human beings is important and the most effective way of passing information. Humans are also able to communicate with machines for instance, computers, where keyboards and typing are the means of communication. Most people can speak but not everyone can read o...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
Department of Electrical Engineering
2024
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| Summary: | [page 73 missing] Communication between human beings is important and the most effective way of passing information. Humans are also able to communicate with machines for instance, computers, where keyboards and typing are the means of communication. Most people can speak but not everyone can read or write. Therefore, if we could get the machines to understand human speech, we could be able to communicate with people (and even make communicating with computers open to many people). This is the main motivation behind Automatic Speech Recognition (ASR) as a field of research, to enable machines to recognize human speech. Automatic Speech Recognition may then be defined as a process carried out by a machine to extract information contained in a captured acoustic speech signal and converting it into words. |
|---|