Multi-path, context dependent SC-HMM architectures for improved connected word recognition
نویسندگان
چکیده
Connected Word Recognition (CWR) systems are needed for many consumer applications. In such applications cost is a major factor. Several architectures for HMM based CWR are examined to provide an optimal cost effective configuration. Three architectures were examined: a simple LTR with no skips, LTR with skips (LTR-WS) and MultiPath LTR. The LTR-WS and the MP-LTR were shown to be superior to the simple LTR. The MPLTR exhibited the best results with long strings.
منابع مشابه
Comparison of continuous-density and semi-continuous HMM in isolated words recognition systems
Several types of Semi-Continuous HMM (SC-HMM) have been compared with the Continuous Density HMM (CD-HMM) in the context of Speaker Independent Isolated Words Recognition (SI-IWR). It is demonstrated that for the ten-digit vocabulary (TIDIGITS), the SC-HMM outperforms the CD-HMM when memory constraints are imposed on the system. SC-HMMs demonstrate recognition rate of about 95% with a total of ...
متن کاملContext-Dependent Classes in a Hybrid Recurrent Network-HMM Speech Recognition System
A method for incorporating context-dependent phone classes in a connectionist-HMM hybrid speech recognition system is introduced. A modular approach is adopted, where single-layer networks discriminate between different context classes given the phone class and the acoustic data. The context networks are combined with a context-independent (CI) network to generate context-dependent (CD) phone p...
متن کاملAn optimized multi-duration HMM for spontaneous speech recognition
In spontaneous speech, various speech style and speed changes can be observed, which are known to degrade speech recognition accuracy. In this paper, we describe an optimized multi-duration HMM (OMD). An OMD is a kind of multi-path HMM with at most two parallel paths. Each path is trained using speech samples with short or long phoneme duration. The thresholds to divide samples of phonemes are ...
متن کاملSpeaker adaptation for context-dependent HMM using spatial relation of both phoneme context hierarchy and speakers
To realize good speaker adaptation for context dependent HMM using small-size training data, reasonable adaptation of unseen models have to be realized using the relation of appeared models and the training data. In the paper, a new speaker adaptation method for context dependent HMM using two spatial constraints is proposed: 1) spatial relation of the phoneme context hierarchical models, and 2...
متن کاملA Continuous Speech Recognition System Embedding MLP into HMM
Nelson Morgan IntI. Compo Sc. Institute 1947 Center Street. Suite 600 Berkeley. CA 94704. USA We are developing a phoneme based. speaker-dependent continuous speech recognition system embedding a Multilayer Perceptron (MLP) (Le .• a feedforward Artificial Neural Network). into a Hidden Markov Model (HMM) approach. In [Bourlard & Wellekens]. it was shown that MLPs were approximating Maximum a Po...
متن کامل