Phonetic vs. Deep Learning Speech Recognition
Discover the benefits of instant custom vocabulary with deep learning speech recognition to improve accuracy.
phonetic machine learning speech recognition study graphic

Traditionally phonetic speech engines have stayed around despite the significantly lower transcription accuracy because of their ability to spot out of vocabulary words better than dictionary based methods. However, with VoiceBase’s breakthrough feature, Custom Vocabulary, the legacy phonetic based engines can finally be retired and completely replaced by state of the art deep learning speech engines.

VoiceBase correctly identifies 92% of instances of selected custom vocabulary compared with 85% in a standard phonetic search.