MATEC Web Conf.
Volume 214, 20182018 2nd International Conference on Information Processing and Control Engineering (ICIPCE 2018)
|Number of page(s)||5|
|Section||Communication and Signal Processing|
|Published online||15 October 2018|
End-to-End Mandarin Recognition based on Convolution Input
Institute of Information Fusion, Naval Aviation University, 264000 Yantai Shandong, China
The cross-entropy criterion of mainstream neural network training is to classify and optimize each frame of acoustic data, while the continuous speech recognition uses the sequence-level transcription accuracy as a performance measure. In view of this difference, an end-to-end speech recognition system based on sequence level transcription is constructed in this paper. The model uses convolution neural network to deal with the input features, selects the best network structure, and performs two-dimensional convolution in the time and frequency domains. At the same time, neural network uses batch normalization technology to reduce generalization error and speed up training. Finally, the hyper-parameters in decoding process are optimized to improve the modelling effect. Experimental results show that the system performance is improved a lot, better than mainstream speech recognition systems.
© The Authors, published by EDP Sciences, 2018
This is an open access article distributed under the terms of the Creative Commons Attribution License 4.0 (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.