增强语音命令的合成训练数据：从基于ASR的过滤到SSL潜在空间中的域适应
Enhancing Synthetic Training Data for Speech Commands: From ASR-Based Filtering to Domain Adaptation in SSL Latent Space
AI总结：
本研究针对语音命令分类，提出基于ASR的过滤方法提升合成数据质量，并利用CycleGAN在自监督潜在空间中缩小合成与真实语音差距，实验验证了性能提升。
摘要：
合成语音作为数据增强手段在自动语音识别和语音分类任务等领域中日益流行。尽管具有声音克隆能力的新型文本到语音系统允许基于短音频片段使用更多数量的声音，但已知这些系统倾向于产生幻觉，并经常生成质量较差的数据，这很可能对下游任务产生负面影响。在本工作中，我们围绕使用合成语音数据进行零样本学习，针对语音命令分类这一特定任务开展了一系列实验。我们在Google Speech Commands数据集上的结果表明，一种简单的基于ASR的过滤方法能够对生成数据的质量产生重大影响，从而转化为更好的性能。此外，尽管生成的语音数据质量良好，我们也表明当使用自监督（WavLM）特征时，合成语音和真实语音仍然容易被区分，这一方面通过CycleGAN进一步探索，以弥合两种语音材料之间的差距。
英文摘要：
The use of synthetic speech as data augmentation is gaining increasing popularity in fields such as automatic speech recognition and speech classification tasks. Despite novel text-to-speech systems with voice cloning capabilities, that allow the usage of a larger amount of voices based on short audio segments, it is known that these systems tend to hallucinate and oftentimes produce bad data that will most likely have a negative impact on the downstream task. In the present work, we conduct a set of experiments around zero-shot learning with synthetic speech data for the specific task of speech commands classification. Our results on the Google Speech Commands dataset show that a simple ASR-based filtering method can have a big impact in the quality of the generated data, translating to a better performance. Furthermore, despite the good quality of the generated speech data, we also show that synthetic and real speech can still be easily distinguishable when using self-supervised (WavLM) features, an aspect further explored with a CycleGAN to bridge the gap between the two types of speech material.
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。
