DocumentCode
353513
Title
Improving intonational phrasing with syntactic information
Author
Koehn, Philipp ; Abney, Steven ; Hirschberg, Julia ; Collins, Michael
Author_Institution
AT&T Res., Florham Park, NJ, USA
Volume
3
fYear
2000
fDate
2000
Firstpage
1289
Abstract
The prediction of intonational phrase boundaries from raw text is an important step for a text-to-speech system: locating where to place short pauses enables more natural sounding speech, that can be more easily understood. We improved upon earlier work [Hirschberg and Prieto, 1996] by adding syntactic information gained from a high-accuracy parser [Collins, 1999]. We report significant improvement using various experimental setups. We also show that our improved method comes close to interannotator agreement
Keywords
speech synthesis; high-accuracy parser; interannotator agreement; intonational phrase boundaries; intonational phrasing; natural sounding speech; prediction; raw text; syntactic information; text-to-speech system; Decision trees; Machine learning; Magnetic heads; Natural languages; Neural networks; Speech synthesis; Testing;
fLanguage
English
Publisher
ieee
Conference_Titel
Acoustics, Speech, and Signal Processing, 2000. ICASSP '00. Proceedings. 2000 IEEE International Conference on
Conference_Location
Istanbul
ISSN
1520-6149
Print_ISBN
0-7803-6293-4
Type
conf
DOI
10.1109/ICASSP.2000.861813
Filename
861813
Link To Document