# Device-Directed Speech Detection: Regularization via Distillation for Weakly-Supervised Models

arXiv: https://arxiv.org/abs/2203.15975 · HTML: https://mlsanity.com/paper/2203.15975/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 22 references that are in the map.
- First posted on arXiv 30 Mar 2022.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [Device-directed Utterance Detection](https://mlsanity.com/paper/1808.02504/) (2018)
- [Exploring attention mechanism for acoustic-based classification of speech utterances into system-directed and non-system-directed](https://mlsanity.com/paper/1902.00570/) (2019)
- [Unacceptable, where is my privacy? Exploring Accidental Triggers of Smart Speakers](https://mlsanity.com/paper/2008.00508/) (2020)
- [Hybrid Transformer/CTC Networks for Hardware Efficient Voice Triggering](https://mlsanity.com/paper/2008.02323/) (2020)
- [Streaming Transformer for Hardware Efficient Voice Trigger Detection and False Trigger Mitigation](https://mlsanity.com/paper/2105.06598/) (2021)
- [Lattice-based Improvements for Voice Triggering Using Graph Neural Networks](https://mlsanity.com/paper/2001.10822/) (2020)
- [Voice trigger detection from LVCSR hypothesis lattices using bidirectional lattice recurrent neural networks](https://mlsanity.com/paper/2003.00304/) (2020)
- [Improving Device Directedness Classification of Utterances with Semantic Lexical Features](https://mlsanity.com/paper/2010.01949/) (2020)
- [Knowledge Transfer for Efficient On-device False Trigger Mitigation](https://mlsanity.com/paper/2010.10591/) (2020)

## Built on by (most cited first, 5 of 5)

- [Leveraging Large Language Models for Exploiting ASR Uncertainty](https://mlsanity.com/paper/2309.04842/) (2023)
- [SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions](https://mlsanity.com/paper/2501.19377/) (2025)
- [Multimodal Data and Resource Efficient Device-Directed Speech Detection with Large Foundation Models](https://mlsanity.com/paper/2312.03632/) (2023)
- [A Multimodal Approach to Device-Directed Speech Detection with Large Language Models](https://mlsanity.com/paper/2403.14438/) (2024)
- [Adaptive Knowledge Distillation for Device-Directed Speech Detection](https://mlsanity.com/paper/2508.02801/) (2025)

## Abstract (arXiv)

We address the problem of detecting speech directed to a device that does not contain a specific wake-word. Specifically, we focus on audio coming from a touch-based invocation. Mitigating virtual assistants (VAs) activation due to accidental button presses is critical for user experience. While the majority of approaches to false trigger mitigation (FTM) are designed to detect the presence of a target keyword, inferring user intent in absence of keyword is difficult. This also poses a challenge when creating the training/evaluation data for such systems due to inherent ambiguity in the user's data. To this end, we propose a novel FTM approach that uses weakly-labeled training data obtained with a newly introduced data sampling strategy. While this sampling strategy reduces data annotation efforts, the data labels are noisy as the data are not annotated manually. We use these data to train an acoustics-only model for the FTM task by regularizing its loss function via knowledge distillation from an ASR-based (LatticeRNN) model. This improves the model decisions, resulting in 66% gain in accuracy, as measured by equal-error-rate (EER), over the base acoustics-only model. We also show that the ensemble of the LatticeRNN and acoustic-distilled models brings further accuracy improvement of 20%.