Complementary Language Model and Parallel Bi-LRNN for False Trigger Mitigation
This addresses privacy and user experience issues in voice assistants, representing an incremental improvement over existing methods.
The paper tackled the problem of false triggers in voice assistants by proposing a complementary language model and parallel Bi-LRNN classifier, achieving a 38.34% relative reduction in false trigger rate at a fixed false suppression rate, with further improvements of 10.8% from parallel modeling.
False triggers in voice assistants are unintended invocations of the assistant, which not only degrade the user experience but may also compromise privacy. False trigger mitigation (FTM) is a process to detect the false trigger events and respond appropriately to the user. In this paper, we propose a novel solution to the FTM problem by introducing a parallel ASR decoding process with a special language model trained from "out-of-domain" data sources. Such language model is complementary to the existing language model optimized for the assistant task. A bidirectional lattice RNN (Bi-LRNN) classifier trained from the lattices generated by the complementary language model shows a $38.34\%$ relative reduction of the false trigger (FT) rate at the fixed rate of $0.4\%$ false suppression (FS) of correct invocations, compared to the current Bi-LRNN model. In addition, we propose to train a parallel Bi-LRNN model based on the decoding lattices from both language models, and examine various ways of implementation. The resulting model leads to further reduction in the false trigger rate by $10.8\%$.