Abstract:

Few-shot Text-To-Speech （TTS） aims to synthesize speech that closely resembles the original speaker using only a small amount of training data. However， this approach faces challenges in quickly adapting to new speakers and improving the similarity between generated speech and speakers while ensuring high speech quality. Existing models often overlook changes in model features during different adaptation stages， leading to slow improvement of speech similarity. To address these issues， a meta-learning-guided model for adapting to new speakers was proposed. The model was guided by a meta-feature module during the adaptation process， ensuring the improvement of speech similarity while maintaining the quality of generated speech during the adaptation to new speakers. Furthermore， the differentiation of adaptation stages was achieved through a step encoder， thereby enhancing the speed of model adaptation to new speakers. The proposed method was evaluated on the Libri-TTS and VCTK datasets using subjective and objective evaluation metrics. Experimental results show that the Dynamic Time Warping-Mel Cepstral Distortion （DTW-MCD） of the proposed model are 7.450 2 and 6.524 3， respectively. It surpasses other meta-learning methods in terms of synthesized speech similarity and enables faster adaptation to new speakers.

Key words: few-shot generation, Text-To-Speech (TTS), meta-learning, speaker adaption, feature extraction

摘要：

在小样本条件下的语音合成（TTS）要求在仅有少量样本的情况下合成与原说话人相似的语音，然而现有的小样本语音合成面临如下问题：如何快速适配新说话人，并且在保证语音质量的情况下提高生成语音与说话人的相似性。现有模型在适配新说话人的过程中，很少考虑到在不同适配阶段模型特征的变化规律，导致生成语音不能在保证语音质量的情况下快速提升语音相似性。为了解决上述问题，提出一种使用元学习指导模型适配新说话人的方法，模型中通过元特征模块对适配过程进行指导，在适配新说话人过程中提升语音相似度的同时保证生成语音质量；并通过步数编码器区分不同的适配阶段，以提升模型适配新说话人的速度。在Libri-TTS与VCTK数据集上通过主观与客观评价指标，在不同的适配步数下对现有快速适配新说话人的方法进行了比较，实验结果表明所提方法动态时间规整的梅尔倒谱失真（DTW-MCD）分别为7.450 2与6.524 3，在合成语音的相似度上优于其他元学习方法，并且能够更快适配新的说话人。

关键词: 小样本生成, 语音合成, 元学习, 说话人适配, 特征提取