【文件属性】:
文件名称:【8】Deep neural networks
文件大小:593KB
文件格式:PDF
更新时间:2022-09-15 04:41:35
ai 深度学习 学术论文
Most current speech recognition systems use
hidden Markov models (HMMs) to deal with
the temporal variability of speech and
Gaussian mixture models (GMMs) to determine
how well each state of each HMM fits a
frame or a short window of frames of coefficients that represents
the acoustic input. An alternative way to evaluate the fit
is to use a feed-forward neural network that takes several
frames of coefficients as input and produces posterior probabilities
over HMM states as output. Deep neural networks
(DNNs) that have many hidden layers and are trained using
new methods have been shown to outperform GMMs on a variety
of speech recognition benchmarks, sometimes by a large
margin. This article provides an overview of this progress and
represents the shared views of four research groups that have
had recent successes in using DNNs for acoustic modeling in
speech recognition