Fuzzy Clustering Approach Using Data Fusion Theory for Automatic Isolated Word Recognition  

Oleh:

Moshiri, Behzad ; Eslambolchi, Parisa

Jenis: Article from Article
Dalam koleksi: Final Program and Book of Abstracts: The 4th Asian Control Conference, September 25-27, 2002 (Sep. 2002), page 1011-1016.
Topik: Data fusion Theory; K-means Clustering; Fuzzy K-means; Fuzzy Vector Quantization
Fulltext: AC021543.PDF (128.81KB)

Isi artikel

The problem of processing and combination of information provided by different knowledge sources is usually referred as multisensor data fusion In this paper the use of fuzzy clustering algorithms for decision level fusion is proposed for speech recognition purposes. The fuzzy k-means (FKM) and the fuzzy vector quantization (FVQ), are used to combine results provided by various single speech recognition algorithms . In voice processing single voice model rarely models the sound perfectly. To overcome the deficient it is recommended to exploit some different models and estimate the result with data fusion methods to use the benefits of each speech recognition methods. Simulation results showed that fuzzy clustering algorithms have better performances compared with the classical kmeans or other known fusion algorithms

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali