Convolutional density estimation in hidden Markov models for speech recognition

نویسندگان

  • Spyridon Matsoukas
  • George Zavaliagkos
چکیده

In continuous density Hidden Markov Models (HMMs) for speech recognition, the probability density function (pdf) for each state is usually expressed as a mixture of Gaussians. In this paper, we present a model in which the pdf is expressed as the convolution of two densities. We focus on the special case where one of the convolved densities is a M -Gaussian mixture, and the other is a mixture of N impulses. We present the reestimation formulae for the parameters of the M N convolutional model, and suggest two ways for initializing them, the residual K-Means approach, and the deconvolution from a standard HMM with MN Gaussians per state using a genetic algorithm to search for the optimal assignment of Gaussians. Both methods result in a compact representation that requires only O(M +N) storage space for the model parameters, and O(MN) time for training and decoding. We explain how the decoding time can be reduced to O(M + kN), where k < M . Finally, results are shown on the 1996 Hub-4 Development test, demonstrating that a 32 2 convolutional model can achieve performance comparable to that of a standard 64-Gaussian per state model.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

شبکه عصبی پیچشی با پنجره‌های قابل تطبیق برای بازشناسی گفتار

Although, speech recognition systems are widely used and their accuracies are continuously increased, there is a considerable performance gap between their accuracies and human recognition ability. This is partially due to high speaker variations in speech signal. Deep neural networks are among the best tools for acoustic modeling. Recently, using hybrid deep neural network and hidden Markov mo...

متن کامل

Improving 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

Speech enhancement based on hidden Markov model using sparse code shrinkage

This paper presents a new hidden Markov model-based (HMM-based) speech enhancement framework based on the independent component analysis (ICA). We propose analytical procedures for training clean speech and noise models by the Baum re-estimation algorithm and present a Maximum a posterior (MAP) estimator based on Laplace-Gaussian (for clean speech and noise respectively) combination in the HMM ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1999