Ai Feedback
Exact(6)
minimum phone error.
We then applied the minimum phone error (MPE) discriminative training technique described in [17].
Acoustic model training was done using the minimum phone error (MPE) [14] criteria.
First order approximation of the minimum phone error (MPE) objective function is used for question pruning to make tree building efficient.
The GMM-HMM baseline system has 40-Gaussian mixtures per state, trained with maximum likelihood (ML), and refined discriminatively (DT) with the minimum phone error (MPE) criterion.
The resulting DNN (with 5 hidden layers, 1024 neurons in each hidden layer, and 3435 outputs in the output layer) goes through one iteration of sequence training with MPE (minimum phone error) criteria.
Similar(53)
Fig. 5 The progress of phone error rates during training.
Fig. 2 Phone error rate as a function of the pooling size.
We also examine the patterns of phone error reduction and look at the cost-performance tradeoffs.
Fig. 3 Phone error rate as a function of the input context size.
The phone error rates are shown as a function of the pooling size.
Related(14)
minimum measurement error
minimum Bit error
minimum classification error
minimum estimation error
minimum generalization error
minimum prediction error
minimum misclassification error
minimum state error
minimum reconstruction error
minimum percentage error
minimum tracking error
minimum dispersion error
minimum bit error
minimum regression error
Write better and faster with AI suggestions while staying true to your unique style.
Since I tried Ludwig back in 2017, I have been constantly using it in both editing and translation. Ever since, I suggest it to my translators at ProSciEditing.

Justyna Jupowicz-Kozak
CEO of Professional Science Editing for Scientists @ prosciediting.com