# A Multi-Discriminator CycleGAN for Unsupervised Non-Parallel Speech Domain Adaptation

arXiv: https://arxiv.org/abs/1804.00522 · HTML: https://mlsanity.com/paper/1804.00522/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Mar 2018.

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

- [Boosting Cross-Domain Speech Recognition with Self-Supervision](https://mlsanity.com/paper/2206.09783/) (2022)
- [Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models](https://mlsanity.com/paper/2405.14161/) (2024)
- [DarkGAN: Exploiting Knowledge Distillation for Comprehensible Audio Synthesis with GANs](https://mlsanity.com/paper/2108.01216/) (2021)
- [Box-Adapt: Domain-Adaptive Medical Image Segmentation using Bounding BoxSupervision](https://mlsanity.com/paper/2108.08432/) (2021)
- [An Adaptive Learning based Generative Adversarial Network for One-To-One Voice Conversion](https://mlsanity.com/paper/2104.12159/) (2021)
- [VQCPC-GAN: Variable-Length Adversarial Audio Synthesis Using Vector-Quantized Contrastive Predictive Coding](https://mlsanity.com/paper/2105.01531/) (2021)
- [Customizing Speech Recognition Model with Large Language Model Feedback](https://mlsanity.com/paper/2506.11091/) (2025)
- [Unsupervised Domain Adaptation in Speech Recognition using Phonetic Features](https://mlsanity.com/paper/2108.02850/) (2021)
- [Improving Speech Recognition on Noisy Speech via Speech Enhancement with Multi-Discriminators CycleGAN](https://mlsanity.com/paper/2112.06309/) (2021)
- [RSD-GAN: Regularized Sobolev Defense GAN Against Speech-to-Text Adversarial Attacks](https://mlsanity.com/paper/2207.06858/) (2022)

## Abstract (arXiv)

Domain adaptation plays an important role for speech recognition models, in particular, for domains that have low resources. We propose a novel generative model based on cyclic-consistent generative adversarial network (CycleGAN) for unsupervised non-parallel speech domain adaptation. The proposed model employs multiple independent discriminators on the power spectrogram, each in charge of different frequency bands. As a result we have 1) better discriminators that focus on fine-grained details of the frequency features, and 2) a generator that is capable of generating more realistic domain-adapted spectrogram. We demonstrate the effectiveness of our method on speech recognition with gender adaptation, where the model only has access to supervised data from one gender during training, but is evaluated on the other at test time. Our model is able to achieve an average of 7.41% on phoneme error rate, and 11.10% word error rate relative performance improvement as compared to the baseline, on TIMIT and WSJ dataset, respectively. Qualitatively, our model also generates more natural sounding speech, when conditioned on data from the other domain.