Title :
Persian Accents Identification Using an Adaptive Neural Network
Author :
Rabiee, Azam ; Setayeshi, Saeed
Author_Institution :
Comput. Group, IAU - Dolatabad Branch, Esfahan, Iran
Abstract :
Speaker´s accent can reduce the performance of automatic speech recognition systems. This paper considered Persian accent identification using a model includes preprocessing, feature extraction and neural networks. Samples are from five different Persian accents. The performance of the neural networks as an adaptive approach is compared with two statistical approaches. The effect of increasing the number of accents in performance is shown here too.
Keywords :
feature extraction; natural language processing; neural nets; speaker recognition; Persian accents identification; adaptive neural network; automatic speech recognition systems; feature extraction; speaker accent; Adaptive systems; Artificial neural networks; Automatic speech recognition; Biological system modeling; Computer science; Educational technology; Feature extraction; Hidden Markov models; Mel frequency cepstral coefficient; Neural networks; accent identification; artificial neural network; feature extraction;
Conference_Titel :
Education Technology and Computer Science (ETCS), 2010 Second International Workshop on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-6388-6
Electronic_ISBN :
978-1-4244-6389-3
DOI :
10.1109/ETCS.2010.273
