Authors
Georg Heigold, Vincent Vanhoucke, Alan Senior, Patrick Nguyen, M Ranzato, Matthieu Devin, Jeffrey Dean
Publication date
2013/5/26
Conference
2013 IEEE International Conference on Acoustics, Speech and Signal Processing
Pages
8619-8623
Publisher
IEEE
Description
ABSTRACT Today's speech recognition technology is mature enough to be useful for many
practical applications. In this context, it is of paramount importance to train accurate acoustic
models for many languages within given resource constraints such as data, processing
power, and time. Multilingual training has the potential to solve the data issue and close the
performance gap between resource-rich and resourcescarce languages. Neural networks
lend themselves naturally to parameter sharing across languages, and distributed ...
practical applications. In this context, it is of paramount importance to train accurate acoustic
models for many languages within given resource constraints such as data, processing
power, and time. Multilingual training has the potential to solve the data issue and close the
performance gap between resource-rich and resourcescarce languages. Neural networks
lend themselves naturally to parameter sharing across languages, and distributed ...
Scholar articles
G Heigold, V Vanhoucke, A Senior, P Nguyen… - 2013 IEEE International Conference on Acoustics, …, 2013
Dates and citation counts are estimated and are determined automatically by a computer program.