High-Order Markov Random Fields and Their Applications in Cross-Language Speech Recognition
In this paper we study the cross-language speech emotion recognition using high-order Markov random fields, especially the application in Vietnamese speech emotion recognition. First, we extract the basic speech features including pitch frequency, formant frequency and short-term intensity. Based on...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2015-11-01
|
| Series: | Cybernetics and Information Technologies |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/cait-2015-0054 |
| _version_ | 1818393144555732992 |
|---|---|
| author | Zhipeng Jiang Chengwei Huang |
| author_facet | Zhipeng Jiang Chengwei Huang |
| author_sort | Zhipeng Jiang |
| collection | DOAJ |
| description | In this paper we study the cross-language speech emotion recognition using high-order Markov random fields, especially the application in Vietnamese speech emotion recognition. First, we extract the basic speech features including pitch frequency, formant frequency and short-term intensity. Based on the low level descriptor we further construct the statistic features including maximum, minimum, mean and standard deviation. Second, we adopt the high-order Markov random fields (MRF) to optimize the cross-language speech emotion model. The dimensional restrictions may be modeled by MRF. Third, based on the Vietnamese and Chinese database we analyze the efficiency of our emotion recognition system. We adopt the dimensional emotion model (arousal-valence) to verify the efficiency of MRF configuration method. The experimental results show that the high-order Markov random fields can improve the dimensional emotion recognition in the cross-language experiments, and the configuration method shows promising robustness over different languages. |
| first_indexed | 2024-12-14T05:40:39Z |
| format | Article |
| id | doaj.art-6add256c0e564df3841d33f6f6d28f4b |
| institution | Directory Open Access Journal |
| issn | 1314-4081 |
| language | English |
| last_indexed | 2024-12-14T05:40:39Z |
| publishDate | 2015-11-01 |
| publisher | Sciendo |
| record_format | Article |
| series | Cybernetics and Information Technologies |
| spelling | doaj.art-6add256c0e564df3841d33f6f6d28f4b2022-12-21T23:15:02ZengSciendoCybernetics and Information Technologies1314-40812015-11-01154505710.1515/cait-2015-0054High-Order Markov Random Fields and Their Applications in Cross-Language Speech RecognitionZhipeng Jiang0Chengwei Huang1School of Electronics and Information Engineering, Jinling Institute of Technology, Nanjing, ChinaCollege of Physics, Optoelectronics and Energy, Soochow University, Suzhou, ChinaIn this paper we study the cross-language speech emotion recognition using high-order Markov random fields, especially the application in Vietnamese speech emotion recognition. First, we extract the basic speech features including pitch frequency, formant frequency and short-term intensity. Based on the low level descriptor we further construct the statistic features including maximum, minimum, mean and standard deviation. Second, we adopt the high-order Markov random fields (MRF) to optimize the cross-language speech emotion model. The dimensional restrictions may be modeled by MRF. Third, based on the Vietnamese and Chinese database we analyze the efficiency of our emotion recognition system. We adopt the dimensional emotion model (arousal-valence) to verify the efficiency of MRF configuration method. The experimental results show that the high-order Markov random fields can improve the dimensional emotion recognition in the cross-language experiments, and the configuration method shows promising robustness over different languages.https://doi.org/10.1515/cait-2015-0054high-order markov random fieldsspeech emotion recognitioncrossdatabase recognitiondimensional emotion model |
| spellingShingle | Zhipeng Jiang Chengwei Huang High-Order Markov Random Fields and Their Applications in Cross-Language Speech Recognition Cybernetics and Information Technologies high-order markov random fields speech emotion recognition crossdatabase recognition dimensional emotion model |
| title | High-Order Markov Random Fields and Their Applications in Cross-Language Speech Recognition |
| title_full | High-Order Markov Random Fields and Their Applications in Cross-Language Speech Recognition |
| title_fullStr | High-Order Markov Random Fields and Their Applications in Cross-Language Speech Recognition |
| title_full_unstemmed | High-Order Markov Random Fields and Their Applications in Cross-Language Speech Recognition |
| title_short | High-Order Markov Random Fields and Their Applications in Cross-Language Speech Recognition |
| title_sort | high order markov random fields and their applications in cross language speech recognition |
| topic | high-order markov random fields speech emotion recognition crossdatabase recognition dimensional emotion model |
| url | https://doi.org/10.1515/cait-2015-0054 |
| work_keys_str_mv | AT zhipengjiang highordermarkovrandomfieldsandtheirapplicationsincrosslanguagespeechrecognition AT chengweihuang highordermarkovrandomfieldsandtheirapplicationsincrosslanguagespeechrecognition |