# Improving Device Directedness Classification of Utterances with Semantic Lexical Features

arXiv: https://arxiv.org/abs/2010.01949 · HTML: https://mlsanity.com/paper/2010.01949/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Sep 2020.

## Built on by (most cited first, 6 of 6)

- [Streaming Transformer for Hardware Efficient Voice Trigger Detection and False Trigger Mitigation](https://mlsanity.com/paper/2105.06598/) (2021)
- [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)
- [Implicit Acoustic Echo Cancellation for Keyword Spotting and Device-Directed Speech Detection](https://mlsanity.com/paper/2111.10639/) (2021)
- [Device-Directed Speech Detection for Follow-up Conversations Using Large Language Models](https://mlsanity.com/paper/2411.00023/) (2024)

## Abstract (arXiv)

User interactions with personal assistants like Alexa, Google Home and Siri are typically initiated by a wake term or wakeword. Several personal assistants feature "follow-up" modes that allow users to make additional interactions without the need of a wakeword. For the system to only respond when appropriate, and to ignore speech not intended for it, utterances must be classified as device-directed or non-device-directed. State-of-the-art systems have largely used acoustic features for this task, while others have used only lexical features or have added LM-based lexical features. We propose a directedness classifier that combines semantic lexical features with a lightweight acoustic feature and show it is effective in classifying directedness. The mixed-domain lexical and acoustic feature model is able to achieve 14% relative reduction of EER over a state-of-the-art acoustic-only baseline model. Finally, we successfully apply transfer learning and semi-supervised learning to the model to improve accuracy even further.