Please use this identifier to cite or link to this item:
doi:10.22028/D291-25309
Title: | A category based approach for recognition of out-of-vocabulary words |
Author(s): | Gallwitz, Florian Nöth, Elmar Niemann, Heinrich |
Language: | English |
Year of Publication: | 1996 |
SWD key words: | Künstliche Intelligenz |
Free key words: | artificial intelligence |
DDC notations: | 004 Computer science, internet |
Publikation type: | Report |
Abstract: | In almost all applications of automatic speech recognition, especially in spontaneous speech tasks, the recognizer vocabulary cannot cover all occurring words. There is always a significant amount of out-of-vocabulary words even when the vocabulary size is very large. In this paper we present a new approach for the integration of out-of-vocabulary words into statistical language models. We use category information for all words in the training corpus to define a function that gives an approximation of the out-of-vocabulary word emission probability for each word category. This information is integrated into the language models. Although we use a simple acoustic model for out-of-vocabulary words, we achieve a 6% reduction of word error rate on spontaneous speech data with about 5% out-of-vocabulary rate. |
Link to this record: | urn:nbn:de:bsz:291-scidok-53252 hdl:20.500.11880/25365 http://dx.doi.org/10.22028/D291-25309 |
Series name: | Vm-Report / Verbmobil, Verbundvorhaben, [Deutsches Forschungszentrum für Künstliche Intelligenz] |
Series volume: | 132 |
Date of registration: | 13-Jun-2013 |
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_132_96.pdf | 188,59 kB | Adobe PDF | View/Open |
Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.