期刊
2022 IEEE SPOKEN LANGUAGE TECHNOLOGY WORKSHOP, SLT
卷 -, 期 -, 页码 221-228出版社
IEEE
DOI: 10.1109/SLT54892.2023.10023187
关键词
unsupervised learning; speech recognition
Unsupervised speech recognition has the potential to improve Automatic Speech Recognition (ASR) systems for all languages by eliminating pre-processing steps and introducing a self-supervised objective. The wav2vec-U 2.0 method shows improved results in unsupervised recognition across different languages while being conceptually simpler.
Unsupervised speech recognition has shown great potential to make Automatic Speech Recognition (ASR) systems accessible to every language. However, existing methods still heavily rely on hand-crafted pre-processing. Similar to the trend of making supervised speech recognition end-to-end, we introduce wav2vec-U 2.0 which does away with all audio-side preprocessing and improves accuracy through better architecture. In addition, we introduce an auxiliary self-supervised objective that ties model predictions back to the input. Experiments show that wav2vec-U 2.0 improves unsupervised recognition results across different languages while being conceptually simpler.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据