Phonem-based isolated Turkish word recognition with subspace classifier

Author

Keser, Serkan ; Edizkan, Rifat

fYear

2009

fDate

9-11 April 2009

Firstpage

93

Lastpage

96

Abstract

In this study, phoneme-based isolated Turkish word recognition with Common Vector Approach (CVA) has been performed. CVA has been used to classify phonemes. The phoneme sequence obtained from the classification is decoded into the word using redundant hash addressing (RHA). The phoneme-based speech recognition is more suitable than the word-based speech recognition for implementing applications that use different words in their dictionaries. For that reason, in this study the CVA is evaluated to see whether it could be used in phoneme-based word recognition or not. In the experimental study we obtained the word recognition rates 70-80% from randomly selected words in METU database. It might be possible to obtain higher recognition rates by improving the CVA and by using different word decoding techniques.

Keywords

decoding; natural languages; signal classification; speech coding; speech recognition; common vector approach; decoding technique; phonem-based isolated Turkish word recognition; redundant hash addressing; subspace classifier; word-based speech recognition; Art; Databases; Decoding; Dictionaries; Hidden Markov models; Neural networks; Robots; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing and Communications Applications Conference, 2009. SIU 2009. IEEE 17th

Conference_Location

Antalya

Print_ISBN

978-1-4244-4435-9

Electronic_ISBN

978-1-4244-4436-6

Type

conf

DOI

10.1109/SIU.2009.5136340

Filename

5136340