Authors
Samy Bengio, Georg Heigold
Publication date
2014
Description
Abstract Speech recognition systems have used the concept of states as a way to
decompose words into sub-word units for decades. As the number of such states now
reaches the number of words used to train acoustic models, it is interesting to consider
approaches that relax the assumption that words are made of states. We present here an
alternative construction, where words are projected into a continuous embedding space
where words that sound alike are nearby in the Euclidean sense. We show how ...
Total citations
20152016119