← Search

Yizhou Peng

2 accepted papers

2022

Minimum Word Error Training For Non-Autoregressive Transformer-Based Code-Switching ASR

ICASSP 2022accepted

Non-autoregressive end-to-end ASR framework might be potentially appropriate for code-switching recognition task thanks to its inherent property that present output token being independent of historical ones. However, it still under-performs the state-of-the-art autoregressive ASR frameworks. In thi…

Cited by 0SourceScholar
2022

Mining Hard Samples Locally And Globally For Improved Speech Separation

ICASSP 2022accepted

Speech separation dataset typically consists of hard and non-hard samples, and the former is minority and latter majority. The data imbalance problem biases the model towards non-hard samples and weakens the generalization capability. Given that the average separation performance is sufficiently goo…

Cited by 0SourceScholar