With the advance in semiconductor memory and the availability of very large speech corpora (of hundreds to thousands of hours of speech), we would like to revisit the use of discrete hidden Markov model (DHMM) in automatic speech recognition. To estimate the discrete density in a DHMM state, the acoustic space is divided into bins and one simply count the relative amount of observations falling into each bin. With a very large speech corpus, we believe that the number of bins may be greatly increased to get a much higher density than before, and we will call the new models, the high-density discrete hidden Markov model (HDDHMM). Our HDDHMM is different from traditional DHMM in two aspects: firstly, the codebook will have a size in thousands...
Spoken Dialogue Systems (SDS) have evolved over the last three decades from simple single word comma...
We study the problem of parameter estimation in continuous density hidden Markov models (CD-HMMs) fo...
Copyright © 2016 The Institute of Electronics, Information and Communication Engineers. Unsupervised...
Traditionally, discrete hidden Markov models (DHMM) use vector quantized speech feature vectors. In ...
Traditionally, discrete hidden Markov models (DHMM) use vector quantized speech feature vectors. In ...
We investigated two methods to improve the performance of high-density discrete hidden Markov model ...
The paper presents a complete discrete statistical framework, based on a novel vector quantization (...
The duration and spectral dynamics of speech signal are modeled as the duration high-order hidden Ma...
The duration high-order hidden Markov model (DHO-HMM) can capture the dy-namic evolution of a physic...
We describe a sub-vector clustering technique to reduce the memory size and computational cost of co...
Hidden Markov models and their variants are the predominant sequential classification method in such...
In this work, motivated by large margin classifiers in machine learning, we propose a novel method t...
Most contemporary laboratory recognizers require too much memory to run, and are too slow for mass a...
Voice control is one of the perspective areas of interdisciplinary field called Human Machine Interf...
It generally takes a long time and requires a large amount of speech data to train hidden Markov mod...
Spoken Dialogue Systems (SDS) have evolved over the last three decades from simple single word comma...
We study the problem of parameter estimation in continuous density hidden Markov models (CD-HMMs) fo...
Copyright © 2016 The Institute of Electronics, Information and Communication Engineers. Unsupervised...
Traditionally, discrete hidden Markov models (DHMM) use vector quantized speech feature vectors. In ...
Traditionally, discrete hidden Markov models (DHMM) use vector quantized speech feature vectors. In ...
We investigated two methods to improve the performance of high-density discrete hidden Markov model ...
The paper presents a complete discrete statistical framework, based on a novel vector quantization (...
The duration and spectral dynamics of speech signal are modeled as the duration high-order hidden Ma...
The duration high-order hidden Markov model (DHO-HMM) can capture the dy-namic evolution of a physic...
We describe a sub-vector clustering technique to reduce the memory size and computational cost of co...
Hidden Markov models and their variants are the predominant sequential classification method in such...
In this work, motivated by large margin classifiers in machine learning, we propose a novel method t...
Most contemporary laboratory recognizers require too much memory to run, and are too slow for mass a...
Voice control is one of the perspective areas of interdisciplinary field called Human Machine Interf...
It generally takes a long time and requires a large amount of speech data to train hidden Markov mod...
Spoken Dialogue Systems (SDS) have evolved over the last three decades from simple single word comma...
We study the problem of parameter estimation in continuous density hidden Markov models (CD-HMMs) fo...
Copyright © 2016 The Institute of Electronics, Information and Communication Engineers. Unsupervised...