Neural Model Reprogramming with Similarity Based Mapping for Low-Resource Spoken Command Recognition
Not on the map. Why?
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.
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
18 of 41 references.
References · 18
- 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
- 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,380
- 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 752
- 2019vq-wav2vec: Self-Supervised Learning of Discrete Speech Representationscited by 340
- 2017Unsupervised Machine Translation Using Monolingual Corpora Onlycited by 273
- 2020Multi-task self-supervised learning for Robust Speech Recognitioncited by 130
- 2018Adversarial Reprogramming of Neural Networkscited by 116
- 2021Voice2Series: Reprogramming Acoustic Models for Time Series Classificationcited by 91
- 2019Learning Problem-agnostic Speech Representations from Multiple Self-supervised Taskscited by 87
- 2020Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resourcescited by 83
- 2018A neural attention model for speech command recognitioncited by 45
- 2020MatchboxNet: 1D Time-Channel Separable Convolutional Neural Network Architecture for Speech Commands Recognitioncited by 36
6 more
- 2021Learning Efficient Representations for Keyword Spotting with Triplet Losscited by 24
- 2020Training Keyword Spotters with Limited and Synthesized Speech Datacited by 20
- 2017Listening to the World Improves Speech Command Recognitioncited by 8
- 2018Efficient keyword spotting using time delay neural networkscited by 5
- 2020Relational Teacher Student Learning with Neural Label Embedding for Device Adaptation in Acoustic Scene Classificationcited by 5
- 2021Representation based meta-learning for few-shot spoken intent recognitioncited by 5
Built on by
Citing papers per year: 2024: 2; 2025: 1.
3 papers.