基于适配器的轻量级文本转语音系统的未见说话人和语言适配
Unseen Speaker and Language Adaptation for Lightweight Text-To-Speech with Adapters
AI总结：
本文针对轻量级文本转语音系统，通过适配器实现未见说话人和语言的跨语言适配，避免灾难性遗忘，提出口音母语程度的客观指标，并分析适配器配置等因素的影响。
摘要：
本文从适配器的视角研究了轻量级文本转语音（TTS）系统中的跨语言TTS合成问题。具体而言，我们比较了未见说话人适配和未见语言适配任务，目标是合成目标说话人在目标语言中的语音，而该目标说话人在目标语言中没有录音数据。客观评估结果表明，适配器能够有效学习语言特定和说话人特定的信息，使预训练模型能够学习未见的说话人身份或语言，同时避免对原始模型的说话人或语言信息产生灾难性遗忘。此外，为了衡量生成语音在口音方面的母语程度，我们提出并验证了一种受第二语言（L2）学习者发音错误检测技术启发的客观指标。本文还深入分析了适配器的位置、配置以及所用说话人数量的影响。
英文摘要：
In this paper we investigate cross-lingual Text-To-Speech (TTS) synthesis through the lens of adapters, in the context of lightweight TTS systems. In particular, we compare the tasks of unseen speaker and language adaptation with the goal of synthesising a target voice in a target language, in which the target voice has no recordings therein. Results from objective evaluations demonstrate the effectiveness of adapters in learning language-specific and speaker-specific information, allowing pre-trained models to learn unseen speaker identities or languages, while avoiding catastrophic forgetting of the original model's speaker or language information. Additionally, to measure how native the generated voices are in terms of accent, we propose and validate an objective metric inspired by mispronunciation detection techniques in second-language (L2) learners. The paper also provides insights into the impact of adapter placement, configuration and the number of speakers used.
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。
