利用CycleGAN和域间损失改进半监督端到端自动语音识别
Improving Semi-supervised End-to-end Automatic Speech Recognition using CycleGAN and Inter-domain Losses
摘要：
我们提出了一种新的方法，结合CycleGAN和域间损失的半监督端到端自动语音识别。域间丢失的目标是使用共享网络提取语音和文本输入的中间共享表示。CycleGAN使用循环一致性损失和身份映射损失来保留从一个域转换到另一个域后输入特征的相关特征。因此，这两种方法都适合于在不成对的语音-文本输入上训练端到端模型。在本文中，我们利用域间损失和CycleGAN的优势来实现未配对语音和文本输入的更好共享表示，从而改进语音到文本的映射。我们在WSJ eval 92和Voxforge（非英语）上的实验结果显示，字符出错率比基线降低了8~8.5%，在LibriSpeech test_clean上的结果也显示出明显的改善。
英文摘要：
We propose a novel method that combines CycleGAN and inter-domain losses for semi-supervised end-to-end automatic speech recognition. Inter-domain loss targets the extraction of an intermediate shared representation of speech and text inputs using a shared network. CycleGAN uses cycle-consistent loss and the identity mapping loss to preserve relevant characteristics of the input feature after converting from one domain to another. As such, both approaches are suitable to train end-to-end models on unpaired speech-text inputs. In this paper, we exploit the advantages from both inter-domain loss and CycleGAN to achieve better shared representation of unpaired speech and text inputs and thus improve the speech-to-text mapping. Our experimental results on the WSJ eval92 and Voxforge (non English) show 8~8.5% character error rate reduction over the baseline, and the results on LibriSpeech test_clean also show noticeable improvement.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
