Segmental Lvq Training for Phoneme Wise Tied Mixture Density Hmms

نویسنده

  • Mikko Kurimo
چکیده

This work presents training methods and recogni tion experiments for phoneme wise tied mixture den sities in hidden Markov models HMM The system trains speaker dependent but vocabulary independent phoneme models for the recognition of Finnish words The Learning Vector Quantization LVQ methods are applied to increase the discrimination between the phoneme models A segmental LVQ training is pro posed to substitute the LVQ based corrective tuning as a parameter estimation method The experiments indi cate that the new method can provide the corresponding recognition accuracy but with less training and more robustness over the initial models Experiments to up scale the current system by introducing context vectors and larger mixture pools show up to reduction of recognition errors compared to the earlier results in

برای دانلود 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

Hybrid Training Method for Tied Mixture Density Hidden Markov Models Using Learning Vector Quantization and Viterbi Estimation

In this work the output density functions of hidden Markov models are phoneme-wise tied mixture Gaussians. For training these tied mixture density HMMs, modiied versions of the Viterbi training and LVQ based corrective tuning are described. The initialization of the mean vectors of the mixture Gaussians is performed by rst composing small Self-Organizing Maps representing each phoneme and then ...

متن کامل

Using the self-organizing map to speed up the probability density estimation for speech recognition with mixture density HMMs

This paper presents methods to improve the probability density estimation in hidden Markov models for phoneme recognition by exploiting the Self-Organizing Map (SOM) algorithm. The advantage of using the SOM is based on the created approximative topology between the mixture densities by training the Gaussian mean vectors used as the kernel centers by the SOM algorithm. The topology makes the ne...

متن کامل

Comparison results for segmental training algorithms for mixture density HMMs

This work presents experiments on four segmental training algorithms for mixture density HMMs. The segmental versions of SOM and LVQ3 suggested by the author are compared against the conventional segmental K-means and the segmental GPD. The recognition task used as a test bench is the speaker dependent, but vocabulary independent automatic speech recognition. The output density function of each...

متن کامل

Self-organization in mixture densities of HMM based speech recognition

In this paper experiments are presented to apply Self-Organizing Map (SOM) and Learning Vector Quantization (LVQ) for training mixture density hidden Markov models (HMMs) in automatic speech recognition. The decoding of spoken words into text is made using speaker dependent, but vocabulary and context independent phoneme HMMs. Each HMM has a set of states and the output density of each state is...

متن کامل

New Ways to Use Lvq - Codebookstogether with Hidden Markov

We introduce a novel way to employ codebooks trained by Learning Vector Quantization together with hidden Markov models. In previous work, LVQ-codebooks have been used as frame labelers. The resulting label stream has been modeled and decoded by discrete observation HMMs. We present a way to extract more information out of the LVQ stage. This is accomplished by modeling the class-wise quantizat...

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

برای دانلود 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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1996