The 2016 BBN Georgian telephone speech keyword spotting system

25 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Unsupervised Cross-lingual Representation Learning for Speech Recognition (2020, methodology): “1 which outperforms the best system by [41].”
XTREME-S: Evaluating Cross-lingual Speech Representations (2022, background): “Recent work revived this dataset with different preprocessing [16, 17, 18, 4].”
Confidence Estimation and Deletion Prediction Using Bidirectional Recurrent Neural Networks (2018, background): “y in hypothesised words can prove useful for ﬂagging up words that may need to be handled differently. For more challenging scenarios such measure can prove fundamental for achieving high performance [6] and yielding reliable feedback [7]. The development cycle of speech recognisers may itself beneﬁ”