Skip to main content
EURASIP Journal on Advances in Signal Processing

Table 4 Comparison of classification accuracy of different feature extraction methods

From: The construction of Bert fusion model of speech recognition and sensing for South China electricity charge service scenario

Model Selection

Accuracy

Recall

F1 value

BERT feature extraction

0.8714

0.8708

0.8713

Word2Vec feature extraction

0.8643

0.8905

0.8818

Word feature combination model

0.8833

0.8826

0.8826

Back to article page