publication . Other literature type . Article . 2014

Convolutional neural networks for speech recognition

Abdel-rahman Mohamed; Gerald Penn; Ossama Abdel-Hamid; Dong Yu; Li Deng; Hui Jiang;
Open Access
  • Published: 01 Oct 2014
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Abstract
Recently, the hybrid deep neural network (DNN)- hidden Markov model (HMM) has been shown to significantly improve speech recognition performance over the conventional Gaussian mixture model (GMM)-HMM. The performance improvement is partially attributed to the ability of the DNN to model complex correlations in speech features. In this paper, we show that further error rate reduction can be obtained by using convolutional neural networks (CNNs). We first present a concise description of the basic CNN and explain how it can be used for speech recognition. We further propose a limited-weight-sharing scheme that can better model speech features. The special structur...
Subjects
arXiv: Computer Science::SoundComputer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing)Computer Science::Neural and Evolutionary Computation
free text keywords: Speech and Hearing, Media Technology, Linguistics and Language, Signal Processing, Acoustics and Ultrasonics, Instrumentation, Electrical and Electronic Engineering, Convolutional neural network, Artificial intelligence, business.industry, business, Hidden Markov model, Mixture model, Deep learning, Speech recognition, Time delay neural network, TIMIT, Artificial neural network, Pattern recognition, Word error rate, Computer science
Related Organizations
Any information missing or wrong?Report an Issue