首页>
外国专利>
Systems and methods for robust speech recognition using generative adversarial networks
Systems and methods for robust speech recognition using generative adversarial networks
展开▼
机译:使用生成对抗网络的强大语音识别的系统和方法
展开▼
页面导航
摘要
著录项
相似文献
摘要
Described herein are systems and methods for a general, scalable, end-to-end framework that uses a generative adversarial network (GAN) objective to enable robust speech recognition. Encoders trained with the proposed approach enjoy improved invariance by learning to map noisy audio to the same embedding space as that of clean audio. Embodiments of a Wasserstein GAN framework increase the robustness of seq-to-seq models in a scalable, end-to-end fashion. In one or more embodiments, an encoder component is treated as the generator of GAN and is trained to produce indistinguishable embeddings between labeled and unlabeled audio samples. This new robust training approach can learn to induce robustness without alignment or complicated inference pipeline and even where augmentation of audio data is not possible.
展开▼