E-Branchformer: Branchformer with Enhanced merging for speech recognition

Understand

Conformer, combining convolution and self-attention sequentially to capture both local and global information, has shown remarkable performance and is currently regarded as the state-of-the-art for automatic speech recognition (ASR).

• Several other studies have explored integrating convolution and self-attention but they have not managed to match Conformer's performance.
• The recently introduced Branchformer achieves comparable performance to Conformer by using dedicated branches of convolution and self-attention and merging local and global context from each branch.
• In this paper, we propose E-Branchformer, which enhances Branchformer by applying an effective merging method and stacking additional point-wise modules.