Towards high performance LVCSR in speech-to-speech translation system on smart phonesJian XueXiaodong Cuiet al.2011INTERSPEECH 2011
Frame-level AnyBoost for LVCSR with the MMI criterionRyuki TachibanaTakashi Fukudaet al.2011ASRU 2011
From modern standard Arabic to Levantine ASR: Leveraging GALE for dialectsHagen SoltauLidia Manguet al.2011ASRU 2011
Uniform speech parameterization for multi-form segment synthesisAlexander SorinSlava Shechtmanet al.2011INTERSPEECH 2011
Using features from topic models to alleviate over-generation in hierarchical phrase-based translationSongfang HuangBowen Zhou2011INTERSPEECH 2011
A convex hull approach to sparse representations for exemplar-based speech recognitionTara N. SainathDavid Nahamooet al.2011ASRU 2011
Acoustic modeling with bootstrap and restructuring based on full covarianceXiaodong CuiXin Chenet al.2011INTERSPEECH 2011
L 1 vs. L 2 regularization in text classification when learning from labeled featuresSînziana MaziluJosé Iria2011ICMLA 2011
An efficient unified extraction algorithm for bilingual dataChristoph TillmannSanjika Hewavitharana2011INTERSPEECH 2011