|
Edinburgh Research Archive >
Centre for Speech Technology Research >
CSTR publications >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/1842/1280
|
| Title: | Detection of accents, phrase boundaries and sentence modality in German with prosodic features. |
| Authors: | Strom, Volker |
| Issue Date: | 1995 |
| Citation: | In Proc. European Conf. on Speech Communication and Technology, volume 3, pages 2039-2041, Madrid, 1995. |
| Publisher: | International Speech Communication Association |
| Abstract: | In this paper detectors for accents, phrase boundaries, and sentence modality are described which derive prosodic features only from the speech signal and its fundamental frequency to support other modules of a speech understanding system in an early analysis stage, or in cases where no word hypotheses are available. A new method for interpolating and decomposing the fundamental frequency is suggested. The detectors' underlying Gaussian distribution classifiers were trained and tested with approximately 50 minutes of spontaneous speech, yielding recognition rates of 78 percent for accents, 81 percent for phrase boundaries, and 85 percent for sentence modality. |
| Keywords: | speech
prosodic features
accents |
| URI: | http://hdl.handle.net/1842/1280 |
| Appears in Collections: | CSTR publications
|
Items in ERA are protected by copyright, with all rights reserved, unless otherwise indicated.
|
