Language dialect based speech emotion recognition through deep learning techniques
| Autor: | Sandeep Kumar Mathivanan, Prabhu Jayagopal, Muthamilselvan Thangaval, Sukumar Rajendran, Maheshwari Venkatasen, Manivannan Sorakaya Somanathan, Thanapal Pandi, Prasanna Mani |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Structure (mathematical logic)
Linguistics and Language Interpretation (logic) Stop words Computer Applications Computer science business.industry Deep learning computer.software_genre Language and Linguistics Human-Computer Interaction 030507 speech-language pathology & audiology 03 medical and health sciences Semantic similarity Computer Vision and Pattern Recognition Artificial intelligence 0305 other medical science Cluster analysis business computer Software Word (computer architecture) Natural language processing |
| Zdroj: | International Journal of Speech Technology. 24:625-635 |
| ISSN: | 1572-8110 1381-2416 |
| DOI: | 10.1007/s10772-021-09838-8 |
| Popis: | The primordial way of communication is through vocal signals, which pave the way for support between individuals in a social structure. Computer applications provide a way to create Automatic Speech Recognition (ASR) with a combination of Speech Emotion Recognition (SER) to detect and identify emotions in the speech signals. The semantic relatedness of words with abstract concepts proves to be complicated than concrete ideas. An ensemble of different clustering techniques is utilized to automatically segregate sense distinctions in the various dialects of sentences spoken to tackle this issue. The interpretation of word sense of a word may change with time and group of people. The proposed model maps characters to word sense with weights provided by Senticnet with trial-and-error methods and tuning. The proposed model utilizes stop words to distinguish word senses with 72.78% accuracy for regional dialects. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink