Analyzing The Robustness Of Unsupervised Speech Recognition
2021 · Guan-Ting Lin, Chan-Jan Hsu, da-Rong Liu, et al.
Abstract
Unsupervised speech recognition (unsupervised ASR) aims to learn the ASR system with non-parallel speech and text corpus only. Wav2vec-U has shown promising results in unsupervised ASR by self-supervised speech representations coupled with Generative Adversarial Network (GAN) training, but the robustness of the unsupervised ASR framework is unknown. In this work, we further analyze the training robustness of unsupervised ASR on the domain mismatch scenarios in which the domains of unpaired speech and text are different. Three domain mismatch scenarios include: (1) using speech and text from different datasets, (2) utilizing noisy/spontaneous speech, and (3) adjusting the amount of speech and text data. We also quantify the degree of the domain mismatch by calculating the JS-divergence of phoneme n-gram between the transcription of speech and text. This metric correlates with the performance highly. Experimental results show that domain mismatch leads to inferior performance, but a self
Authors
(none)
Tags
Stats
Related papers
- Unsupervised Domain Adaptation For Robust Speech Recognition Via Variational Autoencoder-based Data Augmentation (2017)14.23
- Extracting Domain Invariant Features By Unsupervised Learning For Robust Automatic Speech Recognition (2018)9.03
- Robust Wav2vec 2.0: Analyzing Domain Shift In Self-supervised Pre-training (2021)25.07
- Investigating Self-supervised, Weakly Supervised And Fully Supervised Training Approaches For Multi-domain Automatic Speech Recognition: A Study On Bangladeshi Bangla (2022)0.00
- A Noise-robust Self-supervised Pre-training Model Based Speech Representation Learning For Automatic Speech Recognition (2022)11.19
- Boosting Cross-domain Speech Recognition With Self-supervision (2022)0.00
- Unsupervised Domain Adaptation For Speech Recognition Via Uncertainty Driven Self-training (2020)12.25
- Unsupervised Speech Recognition (2021)0.00