Phoneme dedicated ANN improves segmental duration model

Teixeira, João Paulo; Freitas, Diamantino Silva

http://hdl.handle.net/10198/1866

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
pdann_improvessegmentaldurationmodel_final_2.pdf		192.68 KB	Adobe PDF	Download

Send Feedback

Authors

Teixeira, João Paulo

Freitas, Diamantino Silva

Abstract(s)

The Phoneme Dedicated Artificial Neural Network (PDANN) segmental duration model consists of a set of ANNs trained specifically for each phoneme segment in order to avoid miscellaneous influence of different types of phoneme segments. Therefore, each ANN is dedicated to predict the duration of a specific phoneme segment. Objective and subjective measurements of the performance of the PDANN model were compared with those of a typical ANN model using the same input features and database. The results indicate a slight, but clear, perceptually perceived preference towards the PDANN.

URI

http://hdl.handle.net/10198/1866

Citation

Teixeira, João Paulo; Freitas, D. (2008). Phoneme dedicated ANN improves segmental duration model. In 4th International Conference on Speech Prosody. Campinas, Brasil.