21 search results - page 1 / 5 » Hybrid HMM BLSTM-RNN for Robust Speech Recognition |
SPEECH
2010
13 years 9 months ago
2010
TSD
2010
Springer
13 years 8 months ago
2010
Springer
The question how to integrate information from different sources in speech decoding is still only partially solved (layered architecture versus integrated search). We investigate t...
NIPS
1997
14 years 6 days ago
1997
In thispaper, we present a novelhybridarchitecture forcontinuousspeech recognition systems. It consists of a continuous HMM system extended by an arbitrary neural network that is ...
ICPR
2006
IEEE
14 years 12 months ago
2006
IEEE
Speech recognition is usually based on Hidden Markov Models (HMMs), which represent the temporal dynamics of speech very efficiently, and Gaussian mixture models, which do non-opt...
ESANN
1998
14 years 7 days ago
1998
Abstract. In this paper, we focus on a novel NN/HMM architecture for continuous speech recognition. The architecture incorporates a neural feature extraction to gain more discrimin...