Multi-stream hidden Markov models (HMMs) have recently been very successful in audio-visual speech recognition, where the audio and visual streams are fused at the final decision...
We present an approach to detecting and recognizing spoken isolated phrases based solely on visual input. We adopt an architecture that first employs discriminative detection of ...
Kate Saenko, Karen Livescu, Michael Siracusa, Kevi...
Abstract— Especially for tasks like automatic meeting transcription, it would be useful to automatically recognize speech also while multiple speakers are talking simultaneously....
Dorothea Kolossa, Shoko Araki, Marc Delcroix, Tomo...
Random projection has been suggested as a means of dimensionality reduction, where the original data are projected onto a subspace using a random matrix. It represents a computati...
Tetsuya Takiguchi, Jeff Bilmes, Mariko Yoshii, Yas...
In current speech recognition systems mainly Short-Time Fourier Transform based features like MFCC are applied. Dropping the short-time stationarity assumption of the voiced speec...