POLISH EMOTIONAL SPEECH RECOGNITION USING ARTIFICAL NEURAL NETWORK
| Autor: | Paweł Powroźnik |
|---|---|
| Rok vydání: | 2014 |
| Předmět: |
lcsh:Mechanical engineering and machinery
Speech recognition media_common.quotation_subject Anger computer.software_genre lcsh:Technology lcsh:TD1-1066 lcsh:Manufactures medicine lcsh:TJ1-1570 Emotion recognition lcsh:Environmental technology. Sanitary engineering media_common Artificial neural network communication lcsh:T Time delay neural network business.industry General Medicine Boredom Sadness lcsh:TA1-2040 Artificial intelligence medicine.symptom lcsh:Engineering (General). Civil engineering (General) business Psychology emotional speech computer Classifier (UML) artificial neural network lcsh:TS1-2301 Natural language processing Neutral state |
| Zdroj: | Advances in Science and Technology Research Journal, Vol 8, Iss 24, Pp 24-27 (2014) |
| ISSN: | 2299-8624 |
| DOI: | 10.12913/22998624/562 |
| Popis: | The article presents the issue of emotion recognition based on polish emotional speech analysis. The Polish database of emotional speech, prepared and shared by the Medical Electronics Division of the Lodz University of Technology, has been used for research. The following parameters extracted from sampled and normalised speech signal has been used for the analysis: energy of signal, speaker’s sex, average value of speech signal and both the minimum and maximum sample value for a given signal. As an emotional state a classifier fof our layers of artificial neural network has been used. The achieved results reach 50% of accuracy. Conducted researches focused on six emotional states: a neutral state, sadness, joy, anger, fear and boredom. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|