# Neural Model Reprogramming with Similarity Based Mapping for Low-Resource Spoken Command Recognition

arXiv: https://arxiv.org/abs/2110.03894 · HTML: https://mlsanity.com/paper/2110.03894/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 41 references that are in the map.
- First posted on arXiv 8 Oct 2021.

## Builds on (most cited first, 18 of 18)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations](https://mlsanity.com/paper/1910.05453/) (2019)
- [Unsupervised Machine Translation Using Monolingual Corpora Only](https://mlsanity.com/paper/1711.00043/) (2017)
- [Multi-task self-supervised learning for Robust Speech Recognition](https://mlsanity.com/paper/2001.09239/) (2020)
- [Adversarial Reprogramming of Neural Networks](https://mlsanity.com/paper/1806.11146/) (2018)
- [Voice2Series: Reprogramming Acoustic Models for Time Series Classification](https://mlsanity.com/paper/2106.09296/) (2021)
- [Learning Problem-agnostic Speech Representations from Multiple Self-supervised Tasks](https://mlsanity.com/paper/1904.03416/) (2019)
- [Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resources](https://mlsanity.com/paper/2007.08714/) (2020)
- [A neural attention model for speech command recognition](https://mlsanity.com/paper/1808.08929/) (2018)
- [MatchboxNet: 1D Time-Channel Separable Convolutional Neural Network Architecture for Speech Commands Recognition](https://mlsanity.com/paper/2004.08531/) (2020)
- [Learning Efficient Representations for Keyword Spotting with Triplet Loss](https://mlsanity.com/paper/2101.04792/) (2021)
- [Training Keyword Spotters with Limited and Synthesized Speech Data](https://mlsanity.com/paper/2002.01322/) (2020)
- [Listening to the World Improves Speech Command Recognition](https://mlsanity.com/paper/1710.08377/) (2017)
- [Efficient keyword spotting using time delay neural networks](https://mlsanity.com/paper/1807.04353/) (2018)
- [Relational Teacher Student Learning with Neural Label Embedding for Device Adaptation in Acoustic Scene Classification](https://mlsanity.com/paper/2008.00110/) (2020)
- [Representation based meta-learning for few-shot spoken intent recognition](https://mlsanity.com/paper/2106.15238/) (2021)

## Built on by (most cited first, 3 of 3)

- [Sample-specific Masks for Visual Reprogramming-based Prompting](https://mlsanity.com/paper/2406.03150/) (2024)
- [SpeechPrompt: Prompting Speech Language Models for Speech Processing Tasks](https://mlsanity.com/paper/2408.13040/) (2024)
- [Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction](https://mlsanity.com/paper/2506.04650/) (2025)

## Abstract (arXiv)

In this study, we propose a novel adversarial reprogramming (AR) approach for low-resource spoken command recognition (SCR), and build an AR-SCR system. The AR procedure aims to modify the acoustic signals (from the target domain) to repurpose a pretrained SCR model (from the source domain). To solve the label mismatches between source and target domains, and further improve the stability of AR, we propose a novel similarity-based label mapping technique to align classes. In addition, the transfer learning (TL) technique is combined with the original AR process to improve the model adaptation capability. We evaluate the proposed AR-SCR system on three low-resource SCR datasets, including Arabic, Lithuanian, and dysarthric Mandarin speech. Experimental results show that with a pretrained AM trained on a large-scale English dataset, the proposed AR-SCR system outperforms the current state-of-the-art results on Arabic and Lithuanian speech commands datasets, with only a limited amount of training data.