Speech emotion recognition algorithm based on spectrogram feature extraction of deep space attention feature
Starts from the extraction and classification modeling of speech emotion features, based on the hybrid convolutional neural network model, the Itti model in feature extraction was improved, including increasing the extraction by local binary mode. The strong correlation features were extracted combi...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Beijing Xintong Media Co., Ltd
2019-07-01
|
| Series: | Dianxin kexue |
| Subjects: | |
| Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2019052/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841530531708141568 |
|---|---|
| author | Jinhua WANG Na YING Chendu ZHU Zhaosen LIU Zhedong CAI |
| author_facet | Jinhua WANG Na YING Chendu ZHU Zhaosen LIU Zhedong CAI |
| author_sort | Jinhua WANG |
| collection | DOAJ |
| description | Starts from the extraction and classification modeling of speech emotion features, based on the hybrid convolutional neural network model, the Itti model in feature extraction was improved, including increasing the extraction by local binary mode. The strong correlation features were extracted combining with the sensitivity of the auditory sensitivity. Then, the constrained extrusion and excitation network structure of the calibration weights were extracted by feature constraints. Finally, a fine-tuning model based on VGGnet and long-short-time memory network hybrid network was formed, further enhancing the ability to express emotions. By validating on the natural sentiment database and the German-German database, the model had a significant increase in the rate of sentiment recognition, which is 8. 43% higher than the benchmark model. At the same time, the recognition effect of the model on the natural database (FAU-AEC) and the Berlin database (EMO-DB) were compared. The experimental results show that the model has a good generalization. |
| format | Article |
| id | doaj-art-8d2cdbc488a545f9ae6682e1d37d85bd |
| institution | Kabale University |
| issn | 1000-0801 |
| language | zho |
| publishDate | 2019-07-01 |
| publisher | Beijing Xintong Media Co., Ltd |
| record_format | Article |
| series | Dianxin kexue |
| spelling | doaj-art-8d2cdbc488a545f9ae6682e1d37d85bd2025-01-15T03:02:37ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012019-07-013510010859589011Speech emotion recognition algorithm based on spectrogram feature extraction of deep space attention featureJinhua WANGNa YINGChendu ZHUZhaosen LIUZhedong CAIStarts from the extraction and classification modeling of speech emotion features, based on the hybrid convolutional neural network model, the Itti model in feature extraction was improved, including increasing the extraction by local binary mode. The strong correlation features were extracted combining with the sensitivity of the auditory sensitivity. Then, the constrained extrusion and excitation network structure of the calibration weights were extracted by feature constraints. Finally, a fine-tuning model based on VGGnet and long-short-time memory network hybrid network was formed, further enhancing the ability to express emotions. By validating on the natural sentiment database and the German-German database, the model had a significant increase in the rate of sentiment recognition, which is 8. 43% higher than the benchmark model. At the same time, the recognition effect of the model on the natural database (FAU-AEC) and the Berlin database (EMO-DB) were compared. The experimental results show that the model has a good generalization.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2019052/emotion recognitiondeep hybrid neural network modelvisual attention mechanism |
| spellingShingle | Jinhua WANG Na YING Chendu ZHU Zhaosen LIU Zhedong CAI Speech emotion recognition algorithm based on spectrogram feature extraction of deep space attention feature Dianxin kexue emotion recognition deep hybrid neural network model visual attention mechanism |
| title | Speech emotion recognition algorithm based on spectrogram feature extraction of deep space attention feature |
| title_full | Speech emotion recognition algorithm based on spectrogram feature extraction of deep space attention feature |
| title_fullStr | Speech emotion recognition algorithm based on spectrogram feature extraction of deep space attention feature |
| title_full_unstemmed | Speech emotion recognition algorithm based on spectrogram feature extraction of deep space attention feature |
| title_short | Speech emotion recognition algorithm based on spectrogram feature extraction of deep space attention feature |
| title_sort | speech emotion recognition algorithm based on spectrogram feature extraction of deep space attention feature |
| topic | emotion recognition deep hybrid neural network model visual attention mechanism |
| url | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2019052/ |
| work_keys_str_mv | AT jinhuawang speechemotionrecognitionalgorithmbasedonspectrogramfeatureextractionofdeepspaceattentionfeature AT naying speechemotionrecognitionalgorithmbasedonspectrogramfeatureextractionofdeepspaceattentionfeature AT chenduzhu speechemotionrecognitionalgorithmbasedonspectrogramfeatureextractionofdeepspaceattentionfeature AT zhaosenliu speechemotionrecognitionalgorithmbasedonspectrogramfeatureextractionofdeepspaceattentionfeature AT zhedongcai speechemotionrecognitionalgorithmbasedonspectrogramfeatureextractionofdeepspaceattentionfeature |