Conformer: Convolution-augmented Transformer for Speech Recognition

• DOI: 10.21437/interspeech.2020-3015
• Publication Date: 2020-10-27T09:22:11Z
• Authors: Anmol Gulati; James Qin; Chung-Cheng Chiu; Niki Parmar; Yu Zhang; Jiahui Yu; Wei Han; Shibo Wang; Zhengdong Zhang; Yonghui Wu; Ruoming Pang
• Keywords: FOS: Computer and information sciences; Computer Science - Machine Learning; Sound (cs.SD); 02 engineering and technology; Computer Science - Sound; Machine Learning (cs.LG); 03 medical and health sciences; Audio and Speech Processing (eess.AS); 0202 electrical engineering, electronic engineering, information engineering; FOS: Electrical engineering, electronic engineering, information engineering; 0305 other medical science; Electrical Engineering and Systems Science - Audio and Speech Processing

Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (RNNs). Transformer models are good at capturing content-based global interactions, while CNNs exploit local features effectively. In this work, we achieve the best of both worlds by studying how to combine convolution neural networks and transformers to model both local and global dependencies of an audio sequence in a parameter-efficient way. To this regard, we propose the convolution-augmented transformer for speech recognition, named Conformer. Conformer significantly outperforms the previous Transformer and CNN based models achieving state-of-the-art accuracies. On the widely used LibriSpeech benchmark, our model achieves WER of 2.1%/4.3% without using a language model and 1.9%/3.9% with an external language model on test/testother. We also observe competitive performance of 2.7%/6.3% with a small model of only 10M parameters.<br/>Submitted to Interspeech 2020<br/>