Conformer: Convolution-augmented Transformer for Speech Recognition. 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.
Keywords for this software
References in zbMATH (referenced in 3 articles )
Showing results 1 to 3 of 3.
- Binbin Zhang, Di Wu, Chao Yang, Xiaoyu Chen, Zhendong Peng, Xiangming Wang, Zhuoyuan Yao, Xiong Wang, Fan Yu, Lei Xie, Xin Lei: WeNet: Production First and Production Ready End-to-End Speech Recognition Toolkit (2021) arXiv
- Evelina Bakhturina, Vitaly Lavrukhin, Boris Ginsburg: NeMo Toolbox for Speech Dataset Construction (2021) arXiv
- Pengcheng Guo, Florian Boyer, Xuankai Chang, Tomoki Hayashi, Yosuke Higuchi, Hirofumi Inaguma, Naoyuki Kamo, Chenda Li, Daniel Garcia-Romero, Jiatong Shi, Jing Shi, Shinji Watanabe, Kun Wei, Wangyou Zhang, Yuekai Zhang: Recent Developments on ESPnet Toolkit Boosted by Conformer (2020) arXiv