Learn More
In this paper, motivated by large margin classifiers in machine learning, we propose a novel method to estimate continuous-density hidden Markov model (CDHMM) for speech recognition according to the principle of maximizing the minimum multiclass separation margin. The approach is named large margin HMM. First, we show this type of large margin HMM(More)
We present our study on semi-supervised Gaussian mixture model (GMM) hidden Markov model (HMM) and deep neural network (DNN) HMM acoustic model training. We analyze the impact of transcription quality and data sampling approach on the performance of the resulting model, and propose a multi-system combination and confidence re-calibration approach to improve(More)
We propose a multi-accent deep neural network acoustic model with an accent-specific top layer and shared bottom hidden layers. The accent-specific top layer is used to model the distinct accent specific patterns. The shared bottom hidden layers allow maximum knowledge sharing between the native and the accent models. This design is particularly attractive(More)
BACKGROUND Schizophrenia is highly complex multifactorial psychiatric disorder with poorly defined etiopathophysiology, which also has manifestations in the immune system. AIMS The aim of this review is to meta-analyze the available evidence regarding the role of immune activation indicated by the T helper cells in order to evaluate etiopathophysiological(More)
We conducted a comparative analytic study on the context-dependent Gaussian mixture hidden Markov model (CD-GMM-HMM) and deep neural network hidden Markov model (CD-DNN-HMM) with respect to the phone discrimination and the robustness performance. We found that the DNN can significantly improve the phone recognition performance for every phoneme with 15.6%(More)
This paper describes the OGI-FONIX large vocabulary system developed for the 1998 broadcast news evaluation. The main differences from our last year's system [1] are: (1) A multiple pass de-coder is used. (2) Long periods of silence are deleted in both training and decoding features. Cepstral mean subtraction is applied individually to automatically derived(More)
Our previous study on maximum relative margin estimation (MRME) of HMM (C. Liu et al., 2005) demonstrated its advantage over the standard minimum classification error (MCE) training. In this paper, we report our recent improvement on MRME. Specifically, two novel approaches are proposed to handle recognition errors in training sets for the MRME. One is a(More)