Robust Wake-Up Word Detection by Two-stage Multi-resolution Ensembles
Not on the map. Why?
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.
Key facts. Cited by 1 paper 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
19 of 35 references.
References · 19
- 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
- 2020Rethinking Attention with Performerscited by 1,601
- 2017Deep Residual Learning for Small-Footprint Keyword Spottingcited by 68
- 2021Broadcasted Residual Learning for Efficient Keyword Spottingcited by 48
- 2021Deep Spoken Keyword Spotting: An Overviewcited by 43
- 2016Trainable Frontend For Robust and Far-Field Keyword Spottingcited by 33
- 2021Self-paced ensemble learning for speech and audio classificationcited by 11
- 2018Data Augmentation for Robust Keyword Spotting under Playback Interferencecited by 8
- 2020Unacceptable, where is my privacy? Exploring Accidental Triggers of Smart Speakerscited by 8
- 2021Audiomer: A Convolutional Transformer For Keyword Spottingcited by 4
- 2022Iterative pseudo-forced alignment by acoustic CTC loss for self-supervised ASR domain adaptationcited by 4
- 2023Unified Keyword Spotting and Audio Tagging on Mobile Devices with Transformerscited by 4
7 more
- 2023DCCRN-KWS: an audio bias based model for noise robust small-footprint keyword spottingcited by 4
- 2022Filterbank Learning for Noise-Robust Small-Footprint Keyword Spottingcited by 3
- 2021Speech Enhancement for Wake-Up-Word detection in Voice Assistantscited by 2
- 2023Fixed-point quantization aware training for on-device keyword-spottingcited by 2
- 2023To Wake-up or Not to Wake-up: Reducing Keyword False Alarm by Successive Refinementcited by 2
- 2023On-Device Constrained Self-Supervised Speech Representation Learning for Keyword Spotting via Knowledge Distillationcited by 2
- 2021Efficient Keyword Spotting by capturing long-range interactions with Temporal Lambda Networkscited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.