After the model training is finished, the test set data are input to the trained model for testing, and the experimental results are showed in Table 2.
A more detailed description about model training is provided below.
Acoustic model training was done using the minimum phone error (MPE) [14] criteria.
The availability of relevant databases for model training is a critical point for ASR systems design.
Note that the process of the model training is reproducible in spite of the randomness on noise injection and model initialization, since the random seed was hard-coded.
The model training was done in an office environment, while in the SV testing phase, the audio signal was corrupted by a Gaussian additive noise.
Model training was based on training data only.
An especially important step in model training is the selection of sites for the positive training set, and, in order to tune performance, the negative training set.
The key step of the statistical model training is the dimensionality reduction of the large set of features from the training data set.
The SVM based model training was done on the remaining 50% of both noncoding and coding RNA and performances were tested on the independent datasets.
