A Train Query System Based on Speech Recognition and Text Correction

DOI

10.2991/essaeme-15.2015.118How to use a DOI?

Keywords

Speech recognition post-processing, Text correction, Natural language processing, Train query

Abstract

This paper presents our recent work towards the development of a train query system based on speech recognition, text correction and natural language processing. The system enhances the accuracy of speech recognition by combining rules and word frequencies. This paper summarizes and classifies the error types of speech recognition in the field of train query, and then brings forth a semantic framework and a word-frequency-precedence mechanism with pinyin-text mapping. For the text after correctly recognizing, the system extracts the origin and the destination by forward-search-backward-match algorithm. And it synthesizes the least transferring algorithm and the shortest path algorithm to find a route. So it has characteristics of humanity and intelligence.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Hui Zhang
AU  - Yongqi Wang
PY  - 2015/10
DA  - 2015/10
TI  - A Train Query System Based on Speech Recognition and Text Correction
BT  - Proceedings of the 2015 International Conference on Economics, Social Science, Arts, Education and Management Engineering
PB  - Atlantis Press
SP  - 541
EP  - 544
SN  - 2352-5398
UR  - https://doi.org/10.2991/essaeme-15.2015.118
DO  - 10.2991/essaeme-15.2015.118
ID  - Zhang2015/10
ER  -