Streaming Small-Footprint Keyword Spotting using Sequence-to-Sequence Models
This work addresses keyword detection in speech recognition for applications like voice assistants, but it is incremental as it builds on existing sequence-to-sequence models.
The authors tackled keyword spotting by developing a streaming system using an RNN-T model with a novel biasing technique, resulting in significant performance improvements over a strong baseline.
We develop streaming keyword spotting systems using a recurrent neural network transducer (RNN-T) model: an all-neural, end-to-end trained, sequence-to-sequence model which jointly learns acoustic and language model components. Our models are trained to predict either phonemes or graphemes as subword units, thus allowing us to detect arbitrary keyword phrases, without any out-of-vocabulary words. In order to adapt the models to the requirements of keyword spotting, we propose a novel technique which biases the RNN-T system towards a specific keyword of interest. Our systems are compared against a strong sequence-trained, connectionist temporal classification (CTC) based "keyword-filler" baseline, which is augmented with a separate phoneme language model. Overall, our RNN-T system with the proposed biasing technique significantly improves performance over the baseline system.