Hybrid architecture based on fuzzy classifier and multiplayer feed-forward neural network for speaker identification
A novel method for speaker identification was proposed which was based on a fuzzy classifier with hyperellipsoidal regions. First, the training data for each class were divided into several clusters. Then, for each cluster, a fuzzy rule with a hyperellipsoidal region was defined around a cluster cen...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2005-01-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/74666704/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841537283325427712 |
|---|---|
| author | ZHANG Ling-hua YANG Zhen ZHENG Bao-yu |
| author_facet | ZHANG Ling-hua YANG Zhen ZHENG Bao-yu |
| author_sort | ZHANG Ling-hua |
| collection | DOAJ |
| description | A novel method for speaker identification was proposed which was based on a fuzzy classifier with hyperellipsoidal regions. First, the training data for each class were divided into several clusters. Then, for each cluster, a fuzzy rule with a hyperellipsoidal region was defined around a cluster center. The evaluation experiments had been conducted to compare the fuzzy hyperellipsoidal classifier with the HMM. It was found that the former classifier can achieve a comparable speaker identification performance to the latter with higher clustering speed. Further research showed that both fuzzy hyperellipsoidal classifier and the HMM worsened the recognition ability when the test data contained noise. To overcome this problem, a hybrid architecture based on fuzzy classifier and multilayer feed-forward neural network （MLFNN） was developed for speaker recognition. The experimental results showed that the new method can achieve a much better identification performance and robustness to the additive noise. |
| format | Article |
| id | doaj-art-8d8ea7a1b3ec4a58808d8b4c9581533c |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2005-01-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-8d8ea7a1b3ec4a58808d8b4c9581533c2025-01-14T08:40:54ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2005-01-0174666704Hybrid architecture based on fuzzy classifier and multiplayer feed-forward neural network for speaker identificationZHANG Ling-huaYANG ZhenZHENG Bao-yuA novel method for speaker identification was proposed which was based on a fuzzy classifier with hyperellipsoidal regions. First, the training data for each class were divided into several clusters. Then, for each cluster, a fuzzy rule with a hyperellipsoidal region was defined around a cluster center. The evaluation experiments had been conducted to compare the fuzzy hyperellipsoidal classifier with the HMM. It was found that the former classifier can achieve a comparable speaker identification performance to the latter with higher clustering speed. Further research showed that both fuzzy hyperellipsoidal classifier and the HMM worsened the recognition ability when the test data contained noise. To overcome this problem, a hybrid architecture based on fuzzy classifier and multilayer feed-forward neural network （MLFNN） was developed for speaker recognition. The experimental results showed that the new method can achieve a much better identification performance and robustness to the additive noise.http://www.joconline.com.cn/zh/article/74666704/speaker recognitionfuzzyhyperellipsoidal classifiermultilayer feed-forward neural network |
| spellingShingle | ZHANG Ling-hua YANG Zhen ZHENG Bao-yu Hybrid architecture based on fuzzy classifier and multiplayer feed-forward neural network for speaker identification Tongxin xuebao speaker recognition fuzzy hyperellipsoidal classifier multilayer feed-forward neural network |
| title | Hybrid architecture based on fuzzy classifier and multiplayer feed-forward neural network for speaker identification |
| title_full | Hybrid architecture based on fuzzy classifier and multiplayer feed-forward neural network for speaker identification |
| title_fullStr | Hybrid architecture based on fuzzy classifier and multiplayer feed-forward neural network for speaker identification |
| title_full_unstemmed | Hybrid architecture based on fuzzy classifier and multiplayer feed-forward neural network for speaker identification |
| title_short | Hybrid architecture based on fuzzy classifier and multiplayer feed-forward neural network for speaker identification |
| title_sort | hybrid architecture based on fuzzy classifier and multiplayer feed forward neural network for speaker identification |
| topic | speaker recognition fuzzy hyperellipsoidal classifier multilayer feed-forward neural network |
| url | http://www.joconline.com.cn/zh/article/74666704/ |
| work_keys_str_mv | AT zhanglinghua hybridarchitecturebasedonfuzzyclassifierandmultiplayerfeedforwardneuralnetworkforspeakeridentification AT yangzhen hybridarchitecturebasedonfuzzyclassifierandmultiplayerfeedforwardneuralnetworkforspeakeridentification AT zhengbaoyu hybridarchitecturebasedonfuzzyclassifierandmultiplayerfeedforwardneuralnetworkforspeakeridentification |