HyperTTS：使用超网络实现文本转语音中的参数高效适配
HyperTTS: Parameter Efficient Adaptation in Text to Speech using Hypernetworks
AI总结：
本文提出HyperTTS，利用超网络根据说话人表示动态生成Adapter参数，以参数高效方式提升TTS的域外说话人适配性能，并在两种设置下达到最先进水平。
摘要：
神经语音合成，即文本转语音（TTS），旨在将信号从文本域转换到语音域。尽管在同一说话人集合上进行训练和测试的TTS架构已经取得显著改进，但域外说话人性能仍面临巨大限制。针对一组新说话人的域适配可以通过为每个新域微调整个模型来实现，但这会造成参数效率低下。Adapter（适配器）为域适配提供了一种参数高效的替代方案，从而可以解决这一问题。尽管Adapter在NLP中广为人知，但语音合成并未从中获得太多改进。在本研究中，我们提出HyperTTS，它包含一个小型可学习网络，即“hypernetwork（超网络）”，用于生成Adapter模块的参数，使我们能够以说话人表示为条件来调节Adapter，并使其成为动态的。在两种域适配设置上的大量评估证明了其有效性：在参数高效范式下达到最先进性能。我们还比较了HyperTTS的不同变体，并在不同研究中与基线进行比较。使用超网络动态适配适配器参数所取得的有前景结果，为域通用的多说话人TTS系统开辟了新途径。音频样本和代码可在https://github.com/declare-lab/HyperTTS获取。
英文摘要：
Neural speech synthesis, or text-to-speech (TTS), aims to transform a signal from the text domain to the speech domain. While developing TTS architectures that train and test on the same set of speakers has seen significant improvements, out-of-domain speaker performance still faces enormous limitations. Domain adaptation on a new set of speakers can be achieved by fine-tuning the whole model for each new domain, thus making it parameter-inefficient. This problem can be solved by Adapters that provide a parameter-efficient alternative to domain adaptation. Although famous in NLP, speech synthesis has not seen much improvement from Adapters. In this work, we present HyperTTS, which comprises a small learnable network, "hypernetwork", that generates parameters of the Adapter blocks, allowing us to condition Adapters on speaker representations and making them dynamic. Extensive evaluations of two domain adaptation settings demonstrate its effectiveness in achieving state-of-the-art performance in the parameter-efficient regime. We also compare different variants of HyperTTS, comparing them with baselines in different studies. Promising results on the dynamic adaptation of adapter parameters using hypernetworks open up new avenues for domain-generic multi-speaker TTS systems. The audio samples and code are available at https://github.com/declare-lab/HyperTTS.
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。
