A Computational Study of Prosodic Structures of Korean for Speech Recognition and Synthesis : Predicting Phonological Boundaries


The Transactions of the Korea Information Processing Society (1994 ~ 2000), Vol. 4, No. 1, pp. 280-287, Jan. 1997
10.3745/KIPSTE.1997.4.1.280,   PDF Download:

Abstract

The introduction of phonological knowledge, especially prosodic information to speech recognition and synthesis system is very important to build successful spoken language systems. First, related works of computational phonology is overviewed and the theoretical and experimental studies of prosodic structures and boundaries in Korean are summarized. The main focus of this study is to decide which prosodic phrasing constituents are in Korean and to find the word boundaries automatically. A total of 2,200 sentences were trained on a simple recurrent network. The results show that the network was able to predict 70% of the boundaries correctly, even though it was not provided with any information other than phonetic features. This method can be combined with other useful information to predict the boundaries more correctly and to help segmentation, which are vital for the successful speech recognition and synthesis systems.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
L. C. Do, "A Computational Study of Prosodic Structures of Korean for Speech Recognition and Synthesis : Predicting Phonological Boundaries," The Transactions of the Korea Information Processing Society (1994 ~ 2000), vol. 4, no. 1, pp. 280-287, 1997. DOI: 10.3745/KIPSTE.1997.4.1.280.

[ACM Style]
Lee Chan Do. 1997. A Computational Study of Prosodic Structures of Korean for Speech Recognition and Synthesis : Predicting Phonological Boundaries. The Transactions of the Korea Information Processing Society (1994 ~ 2000), 4, 1, (1997), 280-287. DOI: 10.3745/KIPSTE.1997.4.1.280.