97 search results - page 13 / 20 » Asymmetric acoustic modeling of mixed language speech |
COLING
2008
13 years 8 months ago
2008
We define the task of incremental or 0lag utterance segmentation, that is, the task of segmenting an ongoing speech recognition stream into utterance units, and present first resu...
CICLING
2004
Springer
14 years 23 days ago
2004
Springer
The construction of a speech recognition system requires a recorded set of phrases to compute the pertinent acoustic models. This set of phrases must be phonetically rich and balan...
ICASSP
2011
IEEE
12 years 11 months ago
2011
IEEE
Duration of phonemic segments provide important cues for distinguishing words in languages such as Arabic. Recently, we proposed a discriminatively estimated joint acoustic, durat...
CCS
2005
ACM
14 years 27 days ago
2005
ACM
We examine the problem of keyboard acoustic emanations. We present a novel attack taking as input a 10-minute sound recording of a user typing English text using a keyboard, and t...
ICASSP
2011
IEEE
12 years 11 months ago
2011
IEEE
We describe a new approach for rescoring speech lattices — with long-span language models or wide-context acoustic models — that does not entail computationally intensive latt...