@Article{jiot.2019.05866,
AUTHOR = {Yue  Zhao, Jianjian  Yue, Wei  Song, Xiaona  Xu, Xiali  Li, Licheng  Wu, Qiang  Ji},
TITLE = {Tibetan Multi-Dialect Speech Recognition Using Latent Regression Bayesian Network and End-To-End Mode},
JOURNAL = {Journal on Internet of Things},
VOLUME = {1},
YEAR = {2019},
NUMBER = {1},
PAGES = {17--23},
URL = {http://www.techscience.com/jiot/v1n1/28983},
ISSN = {2579-0080},
ABSTRACT = {We proposed a method using latent regression Bayesian network (LRBN) to extract the shared speech feature for the input of end-to-end speech recognition model. The structure of LRBN is compact and its parameter learning is fast. Compared with Convolutional Neural Network, it has a simpler and understood structure and less parameters to learn. Experimental results show that the advantage of hybrid LRBN/Bidirectional Long Short-Term Memory-Connectionist Temporal Classification architecture for Tibetan multi-dialect speech recognition, and demonstrate the LRBN is helpful to differentiate among multiple language speech sets.},
DOI = {10.32604/jiot.2019.05866}
}