Please use this identifier to cite or link to this item:
doi:10.22028/D291-25122
Title: | Detection of phrase boundaries and accents |
Author(s): | Kießling, Andreas Kompe, Ralf Niemann, Heinrich Nöth, Elmar Batliner, Anton |
Language: | English |
Year of Publication: | 1994 |
OPUS Source: | Saarbrücken, 1994 |
SWD key words: | Künstliche Intelligenz |
Free key words: | speech recognition hidden Markov models prosody |
DDC notations: | 004 Computer science, internet |
Publikation type: | Report |
Abstract: | On a large speech database read by untrained speakers experiments for the recognition of phrase boundaries and phrase accents were performed. We used durational features as well as features derived from pitch and energy contours and pause information. Different sets of features were compared. For distinguishing three different boundary classes a recognition rate of 75.7% and for distinguishing accentuated from unaccentuated syllables a recognition rate of 88.7% could be achieved. |
Link to this record: | urn:nbn:de:bsz:291-scidok-40721 hdl:20.500.11880/25178 http://dx.doi.org/10.22028/D291-25122 |
Series name: | Vm-Report / Verbmobil, Verbundvorhaben, [Deutsches Forschungszentrum für Künstliche Intelligenz] |
Series volume: | 36 |
Date of registration: | 2-Aug-2011 |
Faculty: | SE - Sonstige Einrichtungen |
Department: | SE - DFKI Deutsches Forschungszentrum für Künstliche Intelligenz |
Collections: | SciDok - Der Wissenschaftsserver der Universität des Saarlandes |
Files for this record:
File | Description | Size | Format | |
---|---|---|---|---|
report_36_94.pdf | 167,47 kB | Adobe PDF | View/Open |
Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.