# Scaling sparsemax based channel selection for speech recognition with ad-hoc microphone arrays

arXiv: https://arxiv.org/abs/2103.15305 · HTML: https://mlsanity.com/paper/2103.15305/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 21 references that are in the map.
- First posted on arXiv 29 Mar 2021.

## Builds on (most cited first, 10 of 10)

- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification](https://mlsanity.com/paper/1602.02068/) (2016)
- [CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings](https://mlsanity.com/paper/2004.09249/) (2020)
- [Far-Field Automatic Speech Recognition](https://mlsanity.com/paper/2009.09395/) (2020)
- [Multi-Stream End-to-End Speech Recognition](https://mlsanity.com/paper/1906.08041/) (2019)
- [Libri-adhoc40: A dataset collected from synchronized ad-hoc microphone arrays](https://mlsanity.com/paper/2103.15118/) (2021)
- [A practical two-stage training strategy for multi-stream end-to-end speech recognition](https://mlsanity.com/paper/1910.10671/) (2019)
- [Deep Ad-hoc Beamforming](https://mlsanity.com/paper/1811.01233/) (2018)
- [Speech enhancement aided end-to-end multi-task learning for voice activity detection](https://mlsanity.com/paper/2010.12484/) (2020)

## Abstract (arXiv)

Recently, speech recognition with ad-hoc microphone arrays has received much attention. It is known that channel selection is an important problem of ad-hoc microphone arrays, however, this topic seems far from explored in speech recognition yet, particularly with a large-scale ad-hoc microphone array. To address this problem, we propose a Scaling Sparsemax algorithm for the channel selection problem of the speech recognition with large-scale ad-hoc microphone arrays. Specifically, we first replace the conventional Softmax operator in the stream attention mechanism of a multichannel end-to-end speech recognition system with Sparsemax, which conducts channel selection by forcing the channel weights of noisy channels to zero. Because Sparsemax punishes the weights of many channels to zero harshly, we propose Scaling Sparsemax which punishes the channels mildly by setting the weights of very noisy channels to zero only. Experimental results with ad-hoc microphone arrays of over 30 channels under the conformer speech recognition architecture show that the proposed Scaling Sparsemax yields a word error rate of over 30% lower than Softmax on simulation data sets, and over 20% lower on semi-real data sets, in test scenarios with both matched and mismatched channel numbers.