# Supervised Contrastive Learning for Accented Speech Recognition

arXiv: https://arxiv.org/abs/2107.00921 · HTML: https://mlsanity.com/paper/2107.00921/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 20 references that are in the map.
- First posted on arXiv 2 Jul 2021.

## Builds on (most cited first, 14 of 14)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [A Theoretical Analysis of Contrastive Unsupervised Representation Learning](https://mlsanity.com/paper/1902.09229/) (2019)
- [WaveGlow: A Flow-based Generative Network for Speech Synthesis](https://mlsanity.com/paper/1811.00002/) (2018)
- [Data Augmenting Contrastive Learning of Speech Representations in the Time Domain](https://mlsanity.com/paper/2007.00991/) (2020)
- [Domain Adversarial Training for Accented Speech Recognition](https://mlsanity.com/paper/1806.02786/) (2018)
- [Learning Fast Adaptation on Cross-Accented Speech Recognition](https://mlsanity.com/paper/2003.01901/) (2020)
- [Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition](https://mlsanity.com/paper/1802.02656/) (2018)

## Built on by (most cited first, 10 of 10)

- [Superficial White Matter Analysis: An Efficient Point-cloud-based Deep Learning Framework with Supervised Contrastive Learning for Consistent Tractography Parcellation across Populations and dMRI Acquisitions](https://mlsanity.com/paper/2207.08975/) (2022)
- [ContraBAR: Contrastive Bayes-Adaptive Deep RL](https://mlsanity.com/paper/2306.02418/) (2023)
- [A Contrastive Learning Approach to Mitigate Bias in Speech Models](https://mlsanity.com/paper/2406.14686/) (2024)
- [Accented Speech Recognition With Accent-specific Codebooks](https://mlsanity.com/paper/2310.15970/) (2023)
- [Robust Vocal Quality Feature Embeddings for Dysphonic Voice Detection](https://mlsanity.com/paper/2211.09858/) (2022)
- [Adapting Automatic Speech Recognition for Accented Air Traffic Control Communications](https://mlsanity.com/paper/2502.20311/) (2025)
- [DyPCL: Dynamic Phoneme-level Contrastive Learning for Dysarthric Speech Recognition](https://mlsanity.com/paper/2501.19010/) (2025)
- [Accent-Invariant Automatic Speech Recognition via Saliency-Driven Spectrogram Masking](https://mlsanity.com/paper/2510.09528/) (2025)
- [SCaLa: Supervised Contrastive Learning for End-to-End Speech Recognition](https://mlsanity.com/paper/2110.04187/) (2021)
- [Contrastive Regularization for Accent-Robust ASR](https://mlsanity.com/paper/2605.03297/) (2026)

## Abstract (arXiv)

Neural network based speech recognition systems suffer from performance degradation due to accented speech, especially unfamiliar accents. In this paper, we study the supervised contrastive learning framework for accented speech recognition. To build different views (similar "positive" data samples) for contrastive learning, three data augmentation techniques including noise injection, spectrogram augmentation and TTS-same-sentence generation are further investigated. From the experiments on the Common Voice dataset, we have shown that contrastive learning helps to build data-augmentation invariant and pronunciation invariant representations, which significantly outperforms traditional joint training methods in both zero-shot and full-shot settings. Experiments show that contrastive learning can improve accuracy by 3.66% (zero-shot) and 3.78% (full-shot) on average, comparing to the joint training method.