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...
In thispaper, we present a novelhybridarchitecture forcontinuousspeech recognition systems. It consists of a continuous HMM system extended by an arbitrary neural network that is ...
We propose a novel multi-stream framework for continuous conversational speech recognition which employs bidirectional Long Short-Term Memory (BLSTM) networks for phoneme predicti...
The context-independent deep belief network (DBN) hidden Markov model (HMM) hybrid architecture has recently achieved promising results for phone recognition. In this work, we pro...
Hidden Conditional Random Fields(HCRF) is a very promising approach to model speech. However, because HCRF computes the score of a hypothesis by summing up linearly weighted featu...