# Listening to the World Improves Speech Command Recognition

arXiv: https://arxiv.org/abs/1710.08377 · HTML: https://mlsanity.com/paper/1710.08377/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2017.

## Built on by (most cited first, 8 of 8)

- [Classical-to-Quantum Transfer Learning for Spoken Command Recognition Based on Quantum Neural Networks](https://mlsanity.com/paper/2110.08689/) (2021)
- [Exploiting Low-Rank Tensor-Train Deep Neural Networks Based on Riemannian Gradient Descent With Illustrations of Speech Processing](https://mlsanity.com/paper/2203.06031/) (2022)
- [Neural Model Reprogramming with Similarity Based Mapping for Low-Resource Spoken Command Recognition](https://mlsanity.com/paper/2110.03894/) (2021)
- [Kernel Clustering with Sigmoid-based Regularization for Efficient Segmentation of Sequential Data](https://mlsanity.com/paper/2106.11541/) (2021)
- [Exploiting Hybrid Models of Tensor-Train Networks for Spoken Command Recognition](https://mlsanity.com/paper/2201.10609/) (2022)
- [Improving Pretrained YAMNet for Enhanced Speech Command Detection via Transfer Learning](https://mlsanity.com/paper/2504.19030/) (2025)
- [End-to-end Keyword Spotting using Xception-1d](https://mlsanity.com/paper/2110.07498/) (2021)
- [An Initialization Schema for Neuronal Networks on Tabular Data](https://mlsanity.com/paper/2311.03996/) (2023)

## Abstract (arXiv)

We study transfer learning in convolutional network architectures applied to the task of recognizing audio, such as environmental sound events and speech commands. Our key finding is that not only is it possible to transfer representations from an unrelated task like environmental sound classification to a voice-focused task like speech command recognition, but also that doing so improves accuracies significantly. We also investigate the effect of increased model capacity for transfer learning audio, by first validating known results from the field of Computer Vision of achieving better accuracies with increasingly deeper networks on two audio datasets: UrbanSound8k and the newly released Google Speech Commands dataset. Then we propose a simple multiscale input representation using dilated convolutions and show that it is able to aggregate larger contexts and increase classification performance. Further, the models trained using a combination of transfer learning and multiscale input representations need only 40% of the training data to achieve similar accuracies as a freshly trained model with 100% of the training data. Finally, we demonstrate a positive interaction effect for the multiscale input and transfer learning, making a case for the joint application of the two techniques.