66 search results - page 3 / 14 » A flat direct model for speech recognition |
ICASSP
2011
IEEE
12 years 9 months ago
2011
IEEE
Structured precision modelling is an important approach to improve the intra-frame correlation modelling of the standard HMM, where Gaussian mixture model with diagonal covariance...
CHI
2010
ACM
13 years 11 months ago
2010
ACM
Speech Dasher allows writing using a combination of speech and a zooming interface. Users first speak what they want to write and then they navigate through the space of recognit...
ICASSP
2011
IEEE
12 years 9 months ago
2011
IEEE
In this paper we present a novel approach to acoustic model training for non-audible murmur (NAM) recognition using normal speech data transformed into NAM data. NAM is extremely ...
FTSIG
2007
13 years 5 months ago
2007
Hidden Markov Models (HMMs) provide a simple and effective framework for modelling time-varying spectral vector sequences. As a consequence, almost all present day large vocabula...
ICASSP
2011
IEEE
12 years 9 months ago
2011
IEEE
In this paper, we present a novel technique for modeling the posterior probability estimates obtained from a neural network directly in the HMM framework using the Dirichlet Mixtu...