# End-to-end Alexa Device Arbitration

arXiv: https://arxiv.org/abs/2112.04914 · HTML: https://mlsanity.com/paper/2112.04914/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 20 references that are in the map.
- First posted on arXiv 8 Dec 2021.

## Builds on (most cited first, 6 of 6)

- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networks](https://mlsanity.com/paper/1807.00129/) (2018)
- [Broadband DOA estimation using Convolutional neural networks trained with noise signals](https://mlsanity.com/paper/1705.00919/) (2017)
- [Sound Source Localization in a Multipath Environment Using Convolutional Neural Networks](https://mlsanity.com/paper/1710.10948/) (2017)
- [Learning to Rank Microphones for Distant Speech Recognition](https://mlsanity.com/paper/2104.02819/) (2021)

## Built on by (most cited first, 2 of 2)

- [Challenges and Opportunities in Multi-device Speech Processing](https://mlsanity.com/paper/2206.15432/) (2022)
- [SPADE: Self-supervised Pretraining for Acoustic DisEntanglement](https://mlsanity.com/paper/2302.01483/) (2023)

## Abstract (arXiv)

We introduce a variant of the speaker localization problem, which we call device arbitration. In the device arbitration problem, a user utters a keyword that is detected by multiple distributed microphone arrays (smart home devices), and we want to determine which device was closest to the user. Rather than solving the full localization problem, we propose an end-to-end machine learning system. This system learns a feature embedding that is computed independently on each device. The embeddings from each device are then aggregated together to produce the final arbitration decision. We use a large-scale room simulation to generate training and evaluation data, and compare our system against a signal processing baseline.