Title :
GMM and ANN Hybrid Model and its Application in Speaker Identification
Author_Institution :
Sch. of Inf., Wuyi Univ., Jiangmen, China
Abstract :
An inter-speaker information ANN(Artificial Neural Networks) method is presented, in which analyze GMM (Gaussian mixture model) speaker identification system performance, and a hybrid GMM and ANN speaker identification system is constructed. Experiments show that higher identification ratio of hybrid GMM and ANN system of speaker identification is gained than that of GMM and MLP (Multilayer Perception).
Keywords :
Gaussian processes; neural nets; speaker recognition; Gaussian mixture model; artificial neural network; interspeaker information; speaker identification; Artificial neural networks; Computer networks; Information analysis; Neural networks; Performance analysis; Speaker recognition; Speech recognition; Statistics; System performance; Testing; ANN (Artificial neural networks); GMM (Gaussian mixture model); Inter-speaker information; Speaker identification;
Conference_Titel :
Natural Computation, 2009. ICNC '09. Fifth International Conference on
Conference_Location :
Tianjin
Print_ISBN :
978-0-7695-3736-8
DOI :
10.1109/ICNC.2009.535
