Semi-Supervised Deep Time-Delay Embedded Clustering for Stress Speech Analysis
Real stressed speech is affected by various aspects (individual characteristics and environment) so that the stress patterns are diverse and different on each individual. To this end, in our previous work, we performed an unsupervised clustering method that able to self-learning manner by mapping th...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-11-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/8/11/1263 |
| _version_ | 1798034559269339136 |
|---|---|
| author | Barlian Henryranu Prasetio Hiroki Tamura Koichi Tanno |
| author_facet | Barlian Henryranu Prasetio Hiroki Tamura Koichi Tanno |
| author_sort | Barlian Henryranu Prasetio |
| collection | DOAJ |
| description | Real stressed speech is affected by various aspects (individual characteristics and environment) so that the stress patterns are diverse and different on each individual. To this end, in our previous work, we performed an unsupervised clustering method that able to self-learning manner by mapping the feature representations of the stress speech and clustering tasks simultaneously, called deep time-delay embedded clustering (DTEC). However, DTEC has not confirmed yet the compatibility between the output class and informational classes. Therefore, we proposed semi-supervised time-delay embedded clustering (SDTEC) as a new framework of semi-supervised in DTEC. SDTEC incorporates the prior information of pairwise constraints in the embedding layer and simultaneously learns the feature representation and the clustering assignments. The prior information was used to guide the clustering procedure so that the points that belong to the incorrect cluster can be corrected. The effectiveness of the proposed SDTEC was evaluated by comparing it with some baseline methods in terms of the clustering error rate (CER). Moreover, to demonstrate SDTEC’s capabilities, we conducted a comprehensive ablation study. Based on experiment results, SDTEC outperformed the baseline methods and achieves state-of-the-art results in semi-supervised clustering. |
| first_indexed | 2024-04-11T20:45:54Z |
| format | Article |
| id | doaj.art-0714a7fd2fee4ef380c3f8234da4cdc6 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-04-11T20:45:54Z |
| publishDate | 2019-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-0714a7fd2fee4ef380c3f8234da4cdc62022-12-22T04:04:02ZengMDPI AGElectronics2079-92922019-11-01811126310.3390/electronics8111263electronics8111263Semi-Supervised Deep Time-Delay Embedded Clustering for Stress Speech AnalysisBarlian Henryranu Prasetio0Hiroki Tamura1Koichi Tanno2Interdisciplinary Graduate School of Agriculture and Engineering, University of Miyazaki, Miyazaki 889-2192, JapanFaculty of Engineering, University of Miyazaki, Miyazaki 889-2192, JapanFaculty of Engineering, University of Miyazaki, Miyazaki 889-2192, JapanReal stressed speech is affected by various aspects (individual characteristics and environment) so that the stress patterns are diverse and different on each individual. To this end, in our previous work, we performed an unsupervised clustering method that able to self-learning manner by mapping the feature representations of the stress speech and clustering tasks simultaneously, called deep time-delay embedded clustering (DTEC). However, DTEC has not confirmed yet the compatibility between the output class and informational classes. Therefore, we proposed semi-supervised time-delay embedded clustering (SDTEC) as a new framework of semi-supervised in DTEC. SDTEC incorporates the prior information of pairwise constraints in the embedding layer and simultaneously learns the feature representation and the clustering assignments. The prior information was used to guide the clustering procedure so that the points that belong to the incorrect cluster can be corrected. The effectiveness of the proposed SDTEC was evaluated by comparing it with some baseline methods in terms of the clustering error rate (CER). Moreover, to demonstrate SDTEC’s capabilities, we conducted a comprehensive ablation study. Based on experiment results, SDTEC outperformed the baseline methods and achieves state-of-the-art results in semi-supervised clustering.https://www.mdpi.com/2079-9292/8/11/1263semi-supervisedclusteringstress speechdeep clusteringdnntdnnprior knowledgepairwise constraints |
| spellingShingle | Barlian Henryranu Prasetio Hiroki Tamura Koichi Tanno Semi-Supervised Deep Time-Delay Embedded Clustering for Stress Speech Analysis Electronics semi-supervised clustering stress speech deep clustering dnn tdnn prior knowledge pairwise constraints |
| title | Semi-Supervised Deep Time-Delay Embedded Clustering for Stress Speech Analysis |
| title_full | Semi-Supervised Deep Time-Delay Embedded Clustering for Stress Speech Analysis |
| title_fullStr | Semi-Supervised Deep Time-Delay Embedded Clustering for Stress Speech Analysis |
| title_full_unstemmed | Semi-Supervised Deep Time-Delay Embedded Clustering for Stress Speech Analysis |
| title_short | Semi-Supervised Deep Time-Delay Embedded Clustering for Stress Speech Analysis |
| title_sort | semi supervised deep time delay embedded clustering for stress speech analysis |
| topic | semi-supervised clustering stress speech deep clustering dnn tdnn prior knowledge pairwise constraints |
| url | https://www.mdpi.com/2079-9292/8/11/1263 |
| work_keys_str_mv | AT barlianhenryranuprasetio semisuperviseddeeptimedelayembeddedclusteringforstressspeechanalysis AT hirokitamura semisuperviseddeeptimedelayembeddedclusteringforstressspeechanalysis AT koichitanno semisuperviseddeeptimedelayembeddedclusteringforstressspeechanalysis |