This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Network Language Model Generated from a Modification Structure-based Language Model Template
Technical Paper
2009-01-1478
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
Natural speech contains a wide variety of expressions, making it much more difficult to recognize than specified verbal commands. We have developed a method using a language model template to generate language models capable of recognizing manifold expressions. This template method is designed on the basis of the modification structure of keywords. The evaluation results for a language model generated with this method showed that it allowed 630,000 command patterns with a high recognition rate of 96%. The results also revealed that the processing speed and memory used for speech recognition with this language model were at a practical level.
Recommended Content
| Technical Paper | Powering Navigation Systems with SMP-Based Multicore Engine |
| Technical Paper | Honda Next Generation Speech User Interface |
| Journal Article | Ford SYNC and Microsoft Windows Embedded Automotive Make Digital Lifestyle a Reality on the Road |
Authors
Topic
Citation
Katsuragawa, K., Saitoh, D., Oono, T., and Tomikashi, M., "Network Language Model Generated from a Modification Structure-based Language Model Template," SAE Technical Paper 2009-01-1478, 2009, https://doi.org/10.4271/2009-01-1478.Also In
Intelligent Vehicle Initiative (IVI) Technology Advanced Controls, 2009
Number: SP-2230; Published: 2009-04-20
Number: SP-2230; Published: 2009-04-20
References
- W3C: Speech Recognition Grammar Specification Version 1.0, http://www.w3.org/TR/204/REC-speech-grammar-20040316/
- Kai M. Nakamura S. “Improvement and Evaluation of the SPOJUS-SYNO Continuous Japanese Speech Recognition System,” Technical Report of the Institute of Electronics, Information and Communication Engineers, SP93-20 49 56 1993
- CaboCha “Yet Another Japanese Dependency Structure Analyzer,” http://chasen.org/taku/software/cabocha (in Japanese)
- Kurohashi S. Kawahara D. Instruction Manual of Japanese Syntax Analyzer KPN version 2.0 University of Kyoto 2005
- Inoue N. “A Method of Processing Unnecessary Words in Spontaneous Speech Utterances using Garbage HMM,” Journal of the Institute of Electronics, Information and Communication Engineers 77 2 215 222 1994