# Device-directed Utterance Detection

arXiv: https://arxiv.org/abs/1808.02504 · HTML: https://mlsanity.com/paper/1808.02504/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Aug 2018.

## Built on by (most cited first, 19 of 19)

- [Streaming Transformer for Hardware Efficient Voice Trigger Detection and False Trigger Mitigation](https://mlsanity.com/paper/2105.06598/) (2021)
- [SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions](https://mlsanity.com/paper/2501.19377/) (2025)
- [Multimodal Large Language Models with Fusion Low Rank Adaptation for Device Directed Speech Detection](https://mlsanity.com/paper/2406.09617/) (2024)
- [Device-Directed Speech Detection: Regularization via Distillation for Weakly-Supervised Models](https://mlsanity.com/paper/2203.15975/) (2022)
- [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)
- [Streaming on-device detection of device directed speech from voice and touch-based invocation](https://mlsanity.com/paper/2110.04656/) (2021)
- [Audio-to-Intent Using Acoustic-Textual Subword Representations from End-to-End ASR](https://mlsanity.com/paper/2210.12134/) (2022)
- [Modality Dropout for Multimodal Device Directed Speech Detection using Verbal and Non-Verbal Features](https://mlsanity.com/paper/2310.15261/) (2023)
- [Streaming Intended Query Detection using E2E Modeling for Continued Conversation](https://mlsanity.com/paper/2208.13322/) (2022)
- [Adaptive Knowledge Distillation for Device-Directed Speech Detection](https://mlsanity.com/paper/2508.02801/) (2025)
- [Implicit Acoustic Echo Cancellation for Keyword Spotting and Device-Directed Speech Detection](https://mlsanity.com/paper/2111.10639/) (2021)
- [Turbo your multi-modal classification with contrastive learning](https://mlsanity.com/paper/2409.09282/) (2024)
- [Device Directedness with Contextual Cues for Spoken Dialog Systems](https://mlsanity.com/paper/2211.13280/) (2022)
- [Text Injection for Capitalization and Turn-Taking Prediction in Speech Models](https://mlsanity.com/paper/2308.07395/) (2023)
- [Device-Directed Speech Detection for Follow-up Conversations Using Large Language Models](https://mlsanity.com/paper/2411.00023/) (2024)
- [Selective Attention System (SAS): Device-Addressed Speech Detection for Real-Time On-Device Voice AI](https://mlsanity.com/paper/2604.08412/) (2026)
- [Not All Speech Is Intent: Adaptive Self-Correcting Inference Layer for Post-ASR False Wake-Up](https://mlsanity.com/paper/2609.12469/) (2026)
- [Do Audio LLMs Listen Before They Act? Diagnosing Acoustic-Context Gating in Voice Agents](https://mlsanity.com/paper/2609.32536/) (2026)

## Abstract (arXiv)

In this work, we propose a classifier for distinguishing device-directed queries from background speech in the context of interactions with voice assistants. Applications include rejection of false wake-ups or unintended interactions as well as enabling wake-word free follow-up queries. Consider the example interaction: "Computer,~play~music", "Computer,~reduce~the~volume". In this interaction, the user needs to repeat the wake-word (Computer) for the second query. To allow for more natural interactions, the device could immediately re-enter listening state after the first query (without wake-word repetition) and accept or reject a potential follow-up as device-directed or background speech. The proposed model consists of two long short-term memory (LSTM) neural networks trained on acoustic features and automatic speech recognition (ASR) 1-best hypotheses, respectively. A feed-forward deep neural network (DNN) is then trained to combine the acoustic and 1-best embeddings, derived from the LSTMs, with features from the ASR decoder. Experimental results show that ASR decoder, acoustic embeddings, and 1-best embeddings yield an equal-error-rate (EER) of 9.3~%, 10.9~% and 20.1~%, respectively. Combination of the features resulted in a 44~% relative improvement and a final EER of 5.2~%.