Title :
Significance of early tagged contextual graphemes in grapheme based speech synthesis and recognition systems
Author :
Anumanchipalli, Gopala Krishna ; Prahallad, Kishore ; Black, Alan W.
Author_Institution :
Language Technol. Inst., Carnegie Mellon Univ., Pittsburgh, PA
fDate :
March 31 2008-April 4 2008
Abstract :
In this paper we present our argument that context information could be used in early stages i.e., during the definition of mapping of the words into sequence of graphemes. We show that the early tagged contextual graphemes play a significant role in improving the performance of grapheme based speech synthesis and speech recognition systems.
Keywords :
computational linguistics; speech recognition; speech synthesis; contextual grapheme; grapheme based speech synthesis; speech recognition system; Context modeling; Dictionaries; Error analysis; Hidden Markov models; Information technology; Investments; Natural languages; Predictive models; Speech recognition; Speech synthesis; Contextual Graphemes; Grapheme; Minority Languages; Speech Recognition; Speech Synthesis;
Conference_Titel :
Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on
Conference_Location :
Las Vegas, NV
Print_ISBN :
978-1-4244-1483-3
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2008.4518692