Phoneme recognition system based on HMM with distributed VQ codebook
نویسندگان
چکیده
In this paper a new variant of HMM named distributed VQ HMM (DVQHMM) is presented. Its main characteristic is the use of a code books distributed on HMM states with a new manner of HMM parameters estimation. Procedures for training and HMM evaluation of each recognition unit are described. Comparative results on an isolated phoneme recognition system are shown, between DVQHMM and conventional VQ HMM. The use of the proposed method improves the performance of the system.
منابع مشابه
Phoneme-based vector quantization in a discrete HMM speech recognizer
The quantization distortion of vector quantization (VQ) is a key element that affects the performance of a discrete hidden Markov modeling (DHMM) system. Many researchers have realized this problem and tried to use integrated feature or multiple codebook in their systems to offset the disadvantage of the conventional VQ. However the computational complexity of those systems is then increased. I...
متن کاملA New Vector Quantization Front-End Process for Discrete HMM Speech Recognition System
The paper presents a complete discrete statistical framework, based on a novel vector quantization (VQ) front-end process. This new VQ approach performs an optimal distribution of VQ codebook components on HMM states. This technique that we named the distributed vector quantization (DVQ) of hidden Markov models, succeeds in unifying acoustic micro-structure and phonetic macro-structure, when th...
متن کاملImproved Vector Quantization Approach for Discrete HMM Speech Recognition System
The paper presents an improved Vector Quantization (VQ) approach for discrete Hidden Markov Models (HMMs). This improved VQ approach performs an optimal distribution of VQ codebook components on HMM states. This technique, that we named the Distributed Vector Quantization (DVQ) of hidden Markov models, succeeds in unifying acoustic microstructure and phonetic macro-structure when the estimation...
متن کاملOptimization of Phoneme-based Vq Codebook in a Dhmm System
A phoneme-based Gaussian mixture VQ codebook can improve the conventional DHMM system performance signiicantly. In this paper, an optimization method for the phoneme-based VQ codebook is proposed. The experimental results shown that the optimized phoneme-based VQ codebook leads to both the improvement of system performance and the reduction of system complexity.
متن کاملImproving Phoneme Sequence Recognition using Phoneme Duration Information in DNN-HSMM
Improving phoneme recognition has attracted the attention of many researchers due to its applications in various fields of speech processing. Recent research achievements show that using deep neural network (DNN) in speech recognition systems significantly improves the performance of these systems. There are two phases in DNN-based phoneme recognition systems including training and testing. Mos...
متن کامل