Abstract
This paper presents the recognition of Cantonese speech commands using a proposed neural fuzzy network with rule switches. By introducing a switch to each rule, the optimal number of rules can be learned. An improved genetic algorithm (GA) is proposed to train the parameters of the membership functions and the optimal rule set for the proposed neural fuzzy network. An application example of Cantonese command recognition in electronic books will be given to illustrate the merits of the proposed approach.
Original language | English |
---|---|
Title of host publication | IEEE International Conference on Fuzzy Systems |
Pages | 208-213 |
Number of pages | 6 |
Publication status | Published - 11 Jul 2003 |
Event | The IEEE International conference on Fuzzy Systems - St. Louis, MO, United States Duration: 25 May 2003 → 28 May 2003 |
Conference
Conference | The IEEE International conference on Fuzzy Systems |
---|---|
Country/Territory | United States |
City | St. Louis, MO |
Period | 25/05/03 → 28/05/03 |
ASJC Scopus subject areas
- Software
- Safety, Risk, Reliability and Quality
- Chemical Health and Safety