The use of the internet for rehabilitation,is an actual approach to optimize the homecare assistance.A web platform is adopted to recognize the correct pronunced words and phrases in voice rehabilitation process,by creating acoustic training model. The acoustic trainig model is implemented by a lonh shot term memory-LSTM-neural network algorithm,classifyng the speech disorder and assigning a score for each test performend online. The platform is managed by a specialist which can select the exercises to perform.The output graphical dashboards facilitate the clinical evalutations and reporting.
ARTIFICIAL NEURAL NETWORK APPLIED ON VOICE ANALYSIS FOR ONLINE REHABILITATION
fabio manca
;angelo vacca
2020-01-01
Abstract
The use of the internet for rehabilitation,is an actual approach to optimize the homecare assistance.A web platform is adopted to recognize the correct pronunced words and phrases in voice rehabilitation process,by creating acoustic training model. The acoustic trainig model is implemented by a lonh shot term memory-LSTM-neural network algorithm,classifyng the speech disorder and assigning a score for each test performend online. The platform is managed by a specialist which can select the exercises to perform.The output graphical dashboards facilitate the clinical evalutations and reporting.File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
4.pdf
non disponibili
Tipologia:
Abstract
Licenza:
NON PUBBLICO - Accesso privato/ristretto
Dimensione
2.97 MB
Formato
Adobe PDF
|
2.97 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
