Improving Word Accuracy with Gabor Feature Extraction.
Google's word accuracy rate rose from below 80% in 2013 to above 90% in 2015.
In the system evaluation, the final results reported a 96.4% Word Accuracy and a 92.2% Semantic Concept Accuracy.
In previous work, these features are used as inputs to neural networks, which improved word accuracy for speech recognition in the presence of noise.
Oracle-based ASR experiments verify this approach, showing an average of 20% relative word accuracy improvements when accurate estimates of the phase spectrum are available.
The experimental results show that when the sentences uttered by the users are out-of-context analysed by the new interface, the word accuracy and sentence understanding rates increase by 93.71 and 77.42% absolute, respectively, regarding the original interface.
Using a combination of these techniques for the connected digits task, word accuracy is increased from 49.5% to 95.3% even with a packet loss rate of 50% and average burst length of 20 feature vectors.
An evaluation with the AURORA-2J noisy continuous digit speech recognition database (Japanese AURORA-2) shows that SPADE combined with adaptive Wiener filtering, cepstral normalization, and the energy parameter achieves average word accuracy rates of 82.58% with clean training and 92.55% with multicondition training.
Figure 5 Word accuracy for LVCSR.
The performance is given in terms of word accuracy (WA).
The word accuracy by CMN without beamforming was 40.46%.
