Contextnet: Improving Convolutional Neural Networks For Automatic Speech Recognition With Global Context
2020 · Wei Han, Zhengdong Zhang, Yu Zhang, et al.
Abstract
Convolutional neural networks (CNN) have shown promising results for end-to-end speech recognition, albeit still behind other state-of-the-art methods in performance. In this paper, we study how to bridge this gap and go beyond with a novel CNN-RNN-transducer architecture, which we call ContextNet. ContextNet features a fully convolutional encoder that incorporates global context information into convolution layers by adding squeeze-and-excitation modules. In addition, we propose a simple scaling method that scales the widths of ContextNet that achieves good trade-off between computation and accuracy. We demonstrate that on the widely used LibriSpeech benchmark, ContextNet achieves a word error rate (WER) of 2.1%/4.6% without external language model (LM), 1.9%/4.1% with LM and 2.9%/7.0% with only 10M parameters on the clean/noisy LibriSpeech test sets. This compares to the previous best published system of 2.0%/4.6% with LM and 3.9%/11.3% with 20M parameters. The superiority of the pro
Authors
(none)
Tags
Stats
Related papers
- Transformers With Convolutional Context For ASR (2019)0.00
- Constrained Convolutional-recurrent Networks To Improve Speech Quality With Low Impact On Recognition Accuracy (2018)5.24
- Advanced Long-context End-to-end Speech Recognition Using Context-expanded Transformers (2021)10.07
- A Dual-staged Context Aggregation Method Towards Efficient End-to-end Speech Enhancement (2019)0.00
- Speaker Representation Learning Using Global Context Guided Channel And Time-frequency Transformations (2020)6.34
- PCNN: A Lightweight Parallel Conformer Neural Network For Efficient Monaural Speech Enhancement (2023)6.77
- Towards Effective And Compact Contextual Representation For Conformer Transducer Speech Recognition Systems (2023)7.16
- Self-consistent Context Aware Conformer Transducer For Speech Recognition (2024)0.00