# Learning Decoupling Features Through Orthogonality Regularization

arXiv: https://arxiv.org/abs/2203.16772 · HTML: https://mlsanity.com/paper/2203.16772/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 24 references that are in the map.
- First posted on arXiv 31 Mar 2022.

## Builds on (most cited first, 9 of 9)

- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [Deep Residual Learning for Small-Footprint Keyword Spotting](https://mlsanity.com/paper/1710.10361/) (2017)
- [Can We Gain More from Orthogonality Regularizations in Training Deep CNNs?](https://mlsanity.com/paper/1810.09102/) (2018)
- [Temporal Convolution for Real-time Keyword Spotting on Mobile Devices](https://mlsanity.com/paper/1904.03814/) (2019)
- [RawNet: Advanced end-to-end deep neural network using raw waveforms for text-independent speaker verification](https://mlsanity.com/paper/1904.08104/) (2019)
- [Attention-based End-to-End Models for Small-Footprint Keyword Spotting](https://mlsanity.com/paper/1803.10916/) (2018)
- [Multi-Task Network for Noise-Robust Keyword Spotting and Speaker Verification using CTC-based Soft VAD and Global Query Attention](https://mlsanity.com/paper/2005.03867/) (2020)
- [Metric Learning for Keyword Spotting](https://mlsanity.com/paper/2005.08776/) (2020)
- [Speaker-Utterance Dual Attention for Speaker and Utterance Verification](https://mlsanity.com/paper/2008.08901/) (2020)

## Built on by (most cited first, 1 of 1)

- [Privacy-Aware Video Anomaly Detection through Orthogonal Subspace Projection](https://mlsanity.com/paper/2605.08651/) (2026)

## Abstract (arXiv)

Keyword spotting (KWS) and speaker verification (SV) are two important tasks in speech applications. Research shows that the state-of-art KWS and SV models are trained independently using different datasets since they expect to learn distinctive acoustic features. However, humans can distinguish language content and the speaker identity simultaneously. Motivated by this, we believe it is important to explore a method that can effectively extract common features while decoupling task-specific features. Bearing this in mind, a two-branch deep network (KWS branch and SV branch) with the same network structure is developed and a novel decoupling feature learning method is proposed to push up the performance of KWS and SV simultaneously where speaker-invariant keyword representations and keyword-invariant speaker representations are expected respectively. Experiments are conducted on Google Speech Commands Dataset (GSCD). The results demonstrate that the orthogonality regularization helps the network to achieve SOTA EER of 1.31% and 1.87% on KWS and SV, respectively.