Přístupnostní navigace
E-application
Search Search Close
Publication result detail
MATĚJKA, P.
Original Title
Courseware for speech recognition
English Title
Type
Paper in proceedings (conference paper)
Original Abstract
This paper describes software called SpeechAnalyzer, that creates readable patterns by integrating different speech features into graphical pictures. The system extracts the phonemic and prosodic features from speech signals and converts them into a visual image using all the most important computational algorithms based on the speech segmentation, e.g. spectrum, line spectral pairs, linear predictive coefficients, cepstral coefficients, pectrograms. These visual representations are very useful for decoding the complex speech code, which is generated by the continuous movements of speech organs.
English abstract
Keywords
speech, speaker, processing, recognition, program
Key words in English
Authors
Released
01.09.2002
Publisher
VUT BRNO
Location
FEEC BUT, Brno, Czech Republic
ISBN
80-214-2172-X
Book
Proceedings of the conference TSP'2002
Pages from
156
Pages count
4
BibTex
@inproceedings{BUT4767, author="Pavel {Matějka}", title="Courseware for speech recognition", booktitle="Proceedings of the conference TSP'2002", year="2002", number="1", pages="4", publisher="VUT BRNO", address="FEEC BUT, Brno, Czech Republic", isbn="80-214-2172-X" }