RobustL2S：利用自监督表示的说话人特定唇语到语音合成
RobustL2S: Speaker-Specific Lip-to-Speech Synthesis exploiting Self-Supervised Representations
AI总结：
RobustL2S提出模块化唇语到语音合成框架，先用非自回归模型从自监督视觉特征解耦语音内容，再用声码器生成波形，在多个数据集上取得最先进性能。
摘要：
在说话人相关的唇语到语音合成（旨在从无声的说话人脸视频生成语音）方面已取得显著进展。当前最先进的方法主要采用非自回归序列到序列架构，直接从唇部表示预测梅尔频谱图或音频波形。我们假设，由于语音内容与环境信息和说话人特征纠缠在一起，直接预测梅尔频谱图会损害训练/模型效率。为此，我们提出了RobustL2S，一个模块化的唇语到语音合成框架。首先，一个非自回归序列到序列模型将自监督视觉特征映射到解耦的语音内容表示。然后，声码器将语音特征转换为原始波形。大量评估证实了我们方案的有效性，在无约束的Lip2Wav数据集以及有约束的GRID和TCD-TIMIT数据集上均取得了最先进的性能。RobustL2S的语音样本可在https://neha-sherin.github.io/RobustL2S/找到。
英文摘要：
Significant progress has been made in speaker dependent Lip-to-Speech synthesis, which aims to generate speech from silent videos of talking faces. Current state-of-the-art approaches primarily employ non-autoregressive sequence-to-sequence architectures to directly predict mel-spectrograms or audio waveforms from lip representations. We hypothesize that the direct mel-prediction hampers training/model efficiency due to the entanglement of speech content with ambient information and speaker characteristics. To this end, we propose RobustL2S, a modularized framework for Lip-to-Speech synthesis. First, a non-autoregressive sequence-to-sequence model maps self-supervised visual features to a representation of disentangled speech content. A vocoder then converts the speech features into raw waveforms. Extensive evaluations confirm the effectiveness of our setup, achieving state-of-the-art performance on the unconstrained Lip2Wav dataset and the constrained GRID and TCD-TIMIT datasets. Speech samples from RobustL2S can be found at https://neha-sherin.github.io/RobustL2S/
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。
