Integrating pre-training for Acoustic Speech Recognition models (IMAGE)

Tsinghua University Press

Integrating pre-training for Acoustic Speech Recognition models

Caption

The phonetic-semantic pre-training (PSP) framework uses “noise-aware curriculum” learning to effectively improve the performance of ASR in noisy environments. integrating warm-up, self-supervised learning, and fine-tuning.

Credit

CAAI Artificial Intelligence Research, Tsinghua University Press

Usage Restrictions

News organizations may use or redistribute this image, with proper attribution, as part of news coverage of this paper only.

License

Original content

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.