Speech recognition with state-based nearest neighbour classifiers

We present a system that uses nearest neighbour classification on the state level of the hidden Markov model. Common speech recognition systems nowadays use Gaussian mixtures with a very high number of densities. We propose to carry this idea to the extreme, such that each observation is a prototype of its own. This approach is well-known and widely used in… (More)

3 Figures & Tables



Citations per Year

Citation Velocity: 4

Averaging 4 citations per year over the last 3 years.

Learn more about how we calculate this metric in our FAQ.