Application of neural networks for the detection of pathological articulation for Serbian phonemes
| Autor: | Ruzica B. Bilibajkic, Drasko Furundzic, Miško Subotić |
|---|---|
| Rok vydání: | 2014 |
| Předmět: |
Speech production
Artificial neural network Computer science business.industry Speech recognition Acoustic model computer.software_genre Speech processing Electronic mail ComputingMethodologies_PATTERNRECOGNITION Artificial intelligence Mel-frequency cepstrum Hidden Markov model Articulation (phonetics) business computer Natural language processing |
| Zdroj: | 2014 22nd Telecommunications Forum Telfor (TELFOR). |
| DOI: | 10.1109/telfor.2014.7034544 |
| Popis: | Bearing in mind the existential significance of speech there is a well-developed approach to the pathology of speech that is used in speech therapy practice. Based on that, some important theoretical principles of a software package for automatic categorization and quantification of the speech production are discussed. This paper presents the results of the artificial neural networks application to the detection of articulation disorders at the level of phoneme. An overview of the results for different topologies of neural networks as well as the various input parameters are shown. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|