Title :
On the impact of sentence length on recognition accuracy
Author :
Valenta, Tomas ; Smidl, Lubos
Author_Institution :
Fac. of Appl. Sci., New Technol. for the Inf. Soc., Univ. of West Bohemia, Plzeň, Czech Republic
Abstract :
The goal of this article is to analyse how the length of utterances affects performance of an automatic speech recognizer (ASR). Benchmarks of an ASR system were performed for utterances of various lengths on English and Czech corpora. Then the observed phenomena are tried to be explained theoretically. Eventually, results are summarized and some conclusions drawn.
Keywords :
natural language processing; speech recognition; ASR system; Czech corpora; English corpora; automatic speech recognizer; sentence length; Accuracy; Acoustics; Entropy; Hidden Markov models; Speech; Speech recognition; Vocabulary; Automatic speech recognition; accuracy; speech analysis;
Conference_Titel :
Signal Processing (ICSP), 2014 12th International Conference on
Conference_Location :
Hangzhou
Print_ISBN :
978-1-4799-2188-1
DOI :
10.1109/ICOSP.2014.7015055
