How MRI data can turn into a synthetic voice
- Date
- Nov 17, 2016
- Time
- 4:00 PM - 5:00 PM
- Speaker
- Jun.-Prof. Peter Birkholz
- Affiliation
- TU Dresden
- Series
- TUD NIC Kolloquium
- Language
- de
- Main Topic
- Psychologie
- Other Topics
- Medizin, Psychologie, Gesellschaft, Philos., Erzieh.
- Description
- In this talk I will briefly describe the generation of speech by a technique called articulatory speech synthesis. This kind of synthesis differs from the conventional method of speech synthesis, which merely concatenates pre-recorded segments of speech. In contrast, articulatory synthesis models the human speech apparatus and simulates acoustic wave propagation and aerodynamics inside the vocal tract. In this respect I will detail how MRI scans of the vocal tract of a person helped to model the speech apparatus for this kind of synthesis. Finally, I will outline some fascinating prospects of this kind of speech synthesis.
- Links
Last modified: Apr 28, 2017, 6:16:57 PM
Location
TUD Falkenbrunnen (FAL 156, , Chemnitzer Str. 46b)01187Dresden
Organizer
Neuroimaging CentreChemnitzer Str.46a01187Dresden
- Phone
- +49 351 463 42063
- Fax
- +49 351 463 42438
- NIC
- Homepage
- http://www.nic-tud.de
Legend
- Biology
- Chemistry
- Civil Eng., Architecture
- Computer Science
- Economics
- Electrical and Computer Eng.
- Environmental Sciences
- for Pupils
- Law
- Linguistics, Literature and Culture
- Materials
- Mathematics
- Mechanical Engineering
- Medicine
- Physics
- Psychology
- Society, Philosophy, Education
- Spin-off/Transfer
- Traffic
- Training
- Welcome
