This paper presents a corrective model for speech recognition of inflected languages. The model, based on a discriminative framework, incorporates word ngrams features as well as ...
Speaker-normalization and -adaptation methods are essential components of state-of-the-art speech recognition systems nowadays. Recently, so-called invariant integration features ...
The REMOS (REverberation MOdeling for Speech recognition) concept for reverberation-robust distant-talking speech recognition, introduced in [1] for melspectral features, is exten...
This paper presents our studies of automatic speech recognition based on electromyographic biosignals captured from the articulatory muscles in the face using surface electrodes. W...
The BYBLOS continuous speech recognition system is applied to on-line cursive handwriting recognition. By exploiting similarities between on-line cursive handwriting and continuou...
John Makhoul, Thad Starner, Richard M. Schwartz, G...