In this paper, we propose an INductive knowledge GRAph eMbedding method, InGram, that can generate embeddings of new relations as well as new entities at inference time.
By learning compact representations of triplets and qualifiers and feeding them into the transformers, we reduce the computation cost of using transformers.
We describe Howl, an open-source wake word detection toolkit with native support for open speech datasets, like Mozilla Common Voice and Google Speech Commands.
Ranked #4 on Keyword Spotting on Google Speech Commands
We show that only a fourth of the final layers need to be fine-tuned to achieve 90% of the original quality.
Overall, our robust, cross-device implementation for keyword spotting realizes a new paradigm for serving neural network applications, and one of our slim models reduces latency by 66% with a minimal decrease in accuracy of 4% from 94% to 90%.