A language-independent personal voice controller with embedded speaker verification

Schlüter, Ralf; Macherey, Wolfgang; Müller, Boris; Ney, Hermann

doi:10.21437/eurospeech.1999-309

Cited by 5 publications

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Model-based MCE bound to the true Bayes' error

Schlüter

Ney²

2001

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

In this letter, we show that the minimum classification error (MCE) criterion gives an upper bound to the true Bayes' error rate independent of the corresponding model distribution. In addition, we show that model-free optimization of the MCE criterion leads to a closed form solution in the asymptotic case of infinite training data. While leading to the Bayes' error rate, the resulting model distribution differs from the true distribution. This suggests that the structure of model distributions trained with the MCE criterion should differ from the structure of the true distributions, as they are usually used in statistical pattern recognition.Index Terms-Error bounds, maximum mutual information (MMI), minimum classification error (MCE), speech recognition, statistical pattern recognition, training criteria.

show abstract

Model-based MCE bound to the true Bayes' error

Schlüter

Ney²

2001

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

show abstract

Discriminative splitting of Gaussian/log-linear mixture HMMs for speech recognition

Tahir

Schlüter

Ney

2011

2011 IEEE Workshop on Automatic Speech Recognition &Amp; Understanding

View full text Add to dashboard Cite

Abstract-This paper presents a method to incorporate mixture density splitting into the acoustic model discriminative log-linear training. The standard method is to obtain a high resolution model by maximum likelihood training and density splitting, and then further training this model discriminatively. For a single Gaussian density per state the log-linear MMI optimization is a global maximum problem, and by further splitting and discriminative training of this model we can get a higher complexity model. The mixture training is not a global maximum problem, nevertheless experimentally we achieve large gains in the objective function and corresponding moderate gains in the word error rate on a large vocabulary corpus

show abstract

Discriminative resolution enhancement in acoustic modelling

Duchateau

Demuynck

Wambacq

2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)

View full text Add to dashboard Cite

The accuracy of the acoustic models in large vocabulary recognition systems can be improved by increasing the resolution in the acoustic feature space. This can be obtained by increasing the number of gaussian densities in the models by splitting of the gaussians.This paper proposes a novel algorithm for this splitting operation. It is based on the phonetic decision tree used for the state tying in context dependent modelling. Advantage of the method is that it improves the capability of the acoustic models to discriminate between the different tied states.The proposed splitting algorithm was evaluated on the Wall Street Journal recognition task. Comparison with a commonly used splitting algorithm clearly shows that our method can provide smaller (thus faster) acoustic models and results in lower error rates.

show abstract

A language-independent personal voice controller with embedded speaker verification

Cited by 5 publications

References 9 publications

Model-based MCE bound to the true Bayes' error

Model-based MCE bound to the true Bayes' error

Discriminative splitting of Gaussian/log-linear mixture HMMs for speech recognition

Discriminative resolution enhancement in acoustic modelling

Contact Info

Product

Resources

About