arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.01950eess.AScs.CLcs.SD
收藏

AlignTTS:一种高效的前馈文本转语音系统

AlignTTS: Efficient Feed-Forward Text-to-Speech System without Explicit Alignment

Ping An Technology (Shenzhen) Co., Ltd.(平安科技(深圳)有限公司)

Zhen Zeng, Jianzong Wang, Ning Cheng, Tian Xia, Jing Xiao

摘要:

针对高效率和性能,我们提出了AlignTTS并行预测梅尔频谱。AlignTTS基于前馈Transformer,它从字符序列中生成Mel谱,每个字符的持续时间由持续时间预测器确定,它不采用Transformer TTS中的注意力机制将文本与Mel谱对齐,而是采用动态规划的方法将对齐损失考虑到训练中所有可能的对齐。在LJSpeech数据集上的实验表明,该模型不仅在平均选项得分(MOS)上优于Transformer TTS 0.03,而且在效率上比实时的快50倍以上。

英文摘要:

Targeting at both high efficiency and performance, we propose AlignTTS to predict the mel-spectrum in parallel. AlignTTS is based on a Feed-Forward Transformer which generates mel-spectrum from a sequence of characters, and the duration of each character is determined by a duration predictor.Instead of adopting the attention mechanism in Transformer TTS to align text to mel-spectrum, the alignment loss is presented to consider all possible alignments in training by use of dynamic programming. Experiments on the LJSpeech dataset show that our model achieves not only state-of-the-art performance which outperforms Transformer TTS by 0.03 in mean option score (MOS), but also a high efficiency which is more than 50 times faster than real-time.

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。

↑