首页>
外国专利>
SYSTEMS AND METHODS FOR A MULTILINGUAL SPEECH RECOGNITION FRAMEWORK
SYSTEMS AND METHODS FOR A MULTILINGUAL SPEECH RECOGNITION FRAMEWORK
展开▼
机译:多语言语音识别框架的系统和方法
展开▼
页面导航
摘要
著录项
相似文献
摘要
Embodiments described herein provide an Adapt-and-Adjust (A2) mechanism for multilingual speech recognition model that combines both adaptation and adjustment methods as an integrated end-to-end training to improve the models' generalization and mitigate the long-tailed issue. Specifically, a multilingual language model mBERT is utilized, and converted into an autoregressive transformer decoder. In addition, a cross-attention module is added to the encoder on top of the mBERT's self-attention layer in order to explore the acoustic space in addition to the text space. The joint training of the encoder and mBERT decoder can bridge the semantic gap between the speech and the text.
展开▼