Εργαλεία και τεχνικές αυτόματης αναγνώρισης ομιλίας από τον υπολογιστή (Bachelor thesis)
Στογιαννίδης, Κωνσταντίνος
The topic of this thesis is to build an accurate automatic speech recognition system. For this purpose we use Kaldi, an open-source toolkit for speech recognition written in C++. First of all, the main process of automatic speech recognition is explained in details. Secondly, the toolkit Kaldi is explained in details. Furthermore, the installation of the Kaldi toolkit is listed. Next, we analyze the steps required to create the speech recognition system. To train our system, we use two different ways of training, monophonic education and simple trifle education.
| Institution and School/Department of submitter: | Σχολή Τεχνολογικών Εφαρμογών / Τμήμα Μηχανικών Πληροφορικής |
| Subject classification: | Automatic speech recognition Αυτόματη αναγνώριση ομιλίας Markov processes Διεργασίες Markov |
| Keywords: | αυτόματη αναγνώριση ομιλίας;ακουστικό μοντέλο;γλωσσικό μοντέλο;νευρωνικα δίκτυα;kaldi;hidden Markov models;automatic speech recognition (ASR),;acoustic model;language model;neural networks |
| Description: | Πτυχιακή Εργασία – Σχολή Τεχνολογικών Εφαρμογών – Τμήμα Μηχανικών Πληροφορικής ,2018 α.α 9570 |
| URI: | http://195.251.240.227/jspui/handle/123456789/15155 |
| Appears in Collections: | Πτυχιακές Εργασίες |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| Stogiannidis.pdf | 1.13 MB | Adobe PDF | View/Open |
Please use this identifier to cite or link to this item:
This item is a favorite for 0 people.
http://195.251.240.227/jspui/handle/123456789/15155
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
