Title :
Multilingual acoustic models for speech recognition and synthesis
Author :
Kunzmann, S. ; Fischer, V. ; Gonzalez, J. ; Emam, O. ; Günther, C. ; Janke, E.
Author_Institution :
Eur. Voice Technol. Dev., IBM Pervasive Comput., Mannheim, Germany
Abstract :
In this paper, we review the design of a common phone alphabet for up to fifteen languages and describe its application in two important components of a seamless multilingual conversational system, namely speech recognition and synthesis. We report on experiments that demonstrate the advantages of multilingual acoustic models both for the recognition of foreign names and non-native speech, and describe the usefulness of a common phone alphabet for the construction of unit selection based mono- and bilingual speech synthesis systems.
Keywords :
computational linguistics; speech recognition; speech synthesis; bilingual speech synthesis; common phonetic alphabet; conversational system; foreign name recognition; multilingual acoustic models; multilingual speech recognition; multilingual speech synthesis; nonnative speech; unit selection based monolingual speech synthesis; Acoustic applications; Internet; Loudspeakers; Mobile handsets; Natural languages; Pervasive computing; Speech recognition; Speech synthesis; Synthesizers; Training data;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on
Print_ISBN :
0-7803-8484-9
DOI :
10.1109/ICASSP.2004.1326652
