118 search results - page 3 / 24 » Combining many alignments for speech to speech translation |
LREC
2008
13 years 6 months ago
2008
The output of a speech recognition system is not always ideal for subsequent downstream processing, in part because speakers themselves often make mistakes. A system would accompl...
AAAI
2012
11 years 7 months ago
2012
Real-time transcription provides deaf and hard of hearing people visual access to spoken content, such as classroom instruction, and other live events. Currently, the only reliabl...
ICA
2004
Springer
13 years 10 months ago
2004
Springer
This paper presents a method for solving the permutation problem of frequency domain blind source separation (BSS) when the number of source signals is large, and the potential sou...
ICASSP
2009
IEEE
13 years 11 months ago
2009
IEEE
This paper addresses selecting between candidate pronunciations for out-of-vocabulary words in speech processing tasks. We introduce a simple, unsupervised method that outperforms...
ICMCS
2000
IEEE
13 years 9 months ago
2000
IEEE
An image-based approach provides an efficient way for visual speech synthesis. In an image-based visual speech synthesis system, a few lip images, namely visemes, are used for ge...