Scholarly record
SPEECH ANALYSIS AND SYNTHESIS FOR HANDICAPPED
Abstract
This bachelor thesis is focused on speech synthesis of Czech language in frequency domain. The resulting software solution consis ts of the analyzer and synthesizer of selected elementary speech units. Speech synthesis is based on the LPC model. The analyzer analyzes an input phoneme unit in WAV format, divides it into microsegmens of length 20 ms and keeps the LPC coefficients, flag (voiced / unvoiced) and the residual prediction error signal. These data are then stored in the XML file. Further, this thesis deals with methods of speech microseg ment analysis - such as determining voice, pitch detection. From the side of resulting speech synthesis it’s about reverse conversion of microsegment parameters into the time domain, phonetic tr anscription, splitting sentences into syllables and their concatenation.
Publication Impact Profile
Publication details
References3
Doc. Dr. Ing. Černocký, J.: Zpracování řečových signál ů – studijní opora http://www.fit.vutbr.cz/study/courses/ZRE/public/opora/zre_opora.pdf
Psutka, J.: Komunikace s počítačem mluvenou řečí. Academia, Praha 1995
JOrbis - Pure Java Ogg Vorbis Decoder: http://www.jcraft.com/jorbis/
View or Download full articleAccess options
SWS access login
Login as SWS Scientific CommitteeLogin as SWS Scientific PartnerLogin as SWS AuthorAuthors and approved SWS contributors will read and export their own linked papers after identity matching by SWS profile, email and SGEM GlobalID.
For librarian assistance: [email protected]
Purchase Instant Access
- Article can be downloaded after successful payment.
- Article may be used according to SWS library access terms.
- Article cannot be redistributed.

