Unsupervised Domain Adaptation by Adversarial Learning for Robust Speech Recognition
Not on the map. Why?
Abstract (arXiv)
In this paper, we investigate the use of adversarial learning for unsupervised adaptation to unseen recording conditions, more specifically, single microphone far-field speech. We adapt neural networks based acoustic models trained with close-talk clean speech to the new recording conditions using untranscribed adaptation data. Our experimental results on Italian SPEECON data set show that our proposed method achieves 19.8% relative word error rate (WER) reduction compared to the unadapted models. Furthermore, this adaptation method is beneficial even when performed on data from another language (i.e. French) giving 12.6% relative WER reduction.
Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). First posted on arXiv 30 Jul 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 1; 2022: 1; 2023: 2.
4 papers.
- 2022Sample-Efficient Unsupervised Domain Adaptation of Speech Recognition Systems A case study for Modern Greekcited by 7
- 2023Modular Domain Adaptation for Conformer-Based Streaming ASRcited by 7
- 2023D4AM: A General Denoising Framework for Downstream Acoustic Modelscited by 1
- 2021Investigation of Densely Connected Convolutional Networks with Domain Adversarial Learning for Noise Robust Speech Recognitioncited by 0
- 2023D4AM: A General Denoising Framework for Downstream Acoustic Models28 Nov 2023
- 2023Modular Domain Adaptation for Conformer-Based Streaming ASR22 May 2023
- 2022Sample-Efficient Unsupervised Domain Adaptation of Speech Recognition Systems A case study for Modern Greek31 Dec 2022
- 2021Investigation of Densely Connected Convolutional Networks with Domain Adversarial Learning for Noise Robust Speech Recognition19 Dec 2021