# Robust Wake-Up Word Detection by Two-stage Multi-resolution Ensembles

arXiv: https://arxiv.org/abs/2310.11379 · HTML: https://mlsanity.com/paper/2310.11379/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 35 references that are in the map.
- First posted on arXiv 17 Oct 2023.

## Builds on (most cited first, 19 of 19)

- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [Deep Residual Learning for Small-Footprint Keyword Spotting](https://mlsanity.com/paper/1710.10361/) (2017)
- [Broadcasted Residual Learning for Efficient Keyword Spotting](https://mlsanity.com/paper/2106.04140/) (2021)
- [Deep Spoken Keyword Spotting: An Overview](https://mlsanity.com/paper/2111.10592/) (2021)
- [Trainable Frontend For Robust and Far-Field Keyword Spotting](https://mlsanity.com/paper/1607.05666/) (2016)
- [Self-paced ensemble learning for speech and audio classification](https://mlsanity.com/paper/2103.11988/) (2021)
- [Data Augmentation for Robust Keyword Spotting under Playback Interference](https://mlsanity.com/paper/1808.00563/) (2018)
- [Unacceptable, where is my privacy? Exploring Accidental Triggers of Smart Speakers](https://mlsanity.com/paper/2008.00508/) (2020)
- [Audiomer: A Convolutional Transformer For Keyword Spotting](https://mlsanity.com/paper/2109.10252/) (2021)
- [Iterative pseudo-forced alignment by acoustic CTC loss for self-supervised ASR domain adaptation](https://mlsanity.com/paper/2210.15226/) (2022)
- [Unified Keyword Spotting and Audio Tagging on Mobile Devices with Transformers](https://mlsanity.com/paper/2303.01812/) (2023)
- [DCCRN-KWS: an audio bias based model for noise robust small-footprint keyword spotting](https://mlsanity.com/paper/2305.12331/) (2023)
- [Filterbank Learning for Noise-Robust Small-Footprint Keyword Spotting](https://mlsanity.com/paper/2211.10565/) (2022)
- [Speech Enhancement for Wake-Up-Word detection in Voice Assistants](https://mlsanity.com/paper/2101.12732/) (2021)
- [Fixed-point quantization aware training for on-device keyword-spotting](https://mlsanity.com/paper/2303.02284/) (2023)
- [To Wake-up or Not to Wake-up: Reducing Keyword False Alarm by Successive Refinement](https://mlsanity.com/paper/2304.03416/) (2023)
- [On-Device Constrained Self-Supervised Speech Representation Learning for Keyword Spotting via Knowledge Distillation](https://mlsanity.com/paper/2307.02720/) (2023)
- [Efficient Keyword Spotting by capturing long-range interactions with Temporal Lambda Networks](https://mlsanity.com/paper/2104.08086/) (2021)

## Built on by (most cited first, 1 of 1)

- ["OK Aura, Be Fair With Me": Demographics-Agnostic Training for Bias Mitigation in Wake-up Word Detection](https://mlsanity.com/paper/2604.05830/) (2026)

## Abstract (arXiv)

Voice-based interfaces rely on a wake-up word mechanism to initiate communication with devices. However, achieving a robust, energy-efficient, and fast detection remains a challenge. This paper addresses these real production needs by enhancing data with temporal alignments and using detection based on two phases with multi-resolution. It employs two models: a lightweight on-device model for real-time processing of the audio stream and a verification model on the server-side, which is an ensemble of heterogeneous architectures that refine detection. This scheme allows the optimization of two operating points. To protect privacy, audio features are sent to the cloud instead of raw audio. The study investigated different parametric configurations for feature extraction to select one for on-device detection and another for the verification model. Furthermore, thirteen different audio classifiers were compared in terms of performance and inference time. The proposed ensemble outperforms our stronger classifier in every noise condition.