Work

Improving Transformer-based Speech Recognition Using Unsupervised Pre-training

Year: 2019
Type: preprint
Abstract: Speech recognition technologies are gaining enormous popularity in various industrial applications. However, building a good speech recognition system usually requires large amounts of transcribed data, which is expensive to collect. To tackle this problem, an unsupervised pre-training method called Masked Predictive Coding is proposed, which can be applied for unsupervised pre-training with Transformer based model. Experiments on HKUST show that using the same training data, we can achieve CER 23.3%, exceeding the best end-to-end model by over 0.2% absolute CER. With more pre-training data, we can further reduce the CER to 21.0%, or a 11.8% relative CER reduction over baseline.
Language: English
Open Access status: green
OpenAlex ID: W2981991061
Cites: 31
Cited by: 110
Related to: 10