A number of decoding strategies for large vocabulary continuous speech recognition
(LVCSR) are examined from the viewpoint of their search space representation. Different …

Advances in speech technology and computing power have created a surge of interest in
the practical application of speech recognition. However, the most accurate speech …

This paper describes a method for the construction of a word graph (or lattice) for large
vocabulary, continuous speech recognition. The advantage of a word graph is that a fairly …

The authors gives a unifying view of the dynamic programming approach to the search
problem. They review the search problem from the statistical point-of-view and show how the …

In this study, we examine how fast decoding of conversational speech with large
vocabularies profits from efficient use of linguistic information, ie language models and …

Low-rank compression of a neural network is one of the popular compression techniques,
where it has been known to have two main challenges. The first challenge is determining the …

Initially introduced in the late 1960s and early 1970s, dynamic programming algorithms
have become increasingly popular in automatic speech recognition. There are two reasons …

This paper presents two look-ahead techniques for speeding up large vocabulary
continuous speech recognition. These two techniques are the language model look-ahead …

Building accurate language models that capture meaningful long-term dependencies is a
core challenge in natural language processing. Towards this end, we present a calibration …

Presents an efficient look-ahead technique which incorporates the language model
knowledge at the earliest possible stage during the search process. This so-called language …