arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.05514eess.AS
收藏

TalkNet:全卷积非自回归语音合成模型

TalkNet: Fully-Convolutional Non-Autoregressive Speech Synthesis Model

Stanislav Beliaev, Yurii Rebryk, Boris Ginsburg

摘要:

我们提出了TalkNet,一个用于语音合成的卷积非自回归神经模型。该模型由两个前馈卷积网络组成。第一个网络预测字素持续时间。通过根据预测的持续时间重复每个符号来扩展输入文本。第二个网络从扩展的文本中生成梅尔频谱图。为了训练字形持续时间预测器,我们使用预先训练的基于连接主义时间分类(CTC)的语音识别模型将字形持续时间添加到训练数据集。显式持续时间预测消除了单词跳过和重复。在LJSpeech数据集上的实验表明,语音质量几乎与自回归模型相匹配。该模型非常紧凑-它有10.8M个参数,几乎比目前最先进的文本到语音模型少3倍。非自回归架构允许快速训练和推理。

英文摘要:

We propose TalkNet, a convolutional non-autoregressive neural model for speech synthesis. The model consists of two feed-forward convolutional networks. The first network predicts grapheme durations. An input text is expanded by repeating each symbol according to the predicted duration. The second network generates a mel-spectrogram from the expanded text. To train a grapheme duration predictor, we add the grapheme duration to the training dataset using a pre-trained Connectionist Temporal Classification (CTC)-based speech recognition model. The explicit duration prediction eliminates word skipping and repeating. Experiments on the LJSpeech dataset show that the speech quality nearly matches auto-regressive models. The model is very compact -- it has 10.8M parameters, almost 3x less than the present state-of-the-art text-to-speech models. The non-autoregressive architecture allows for fast training and inference.

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。

↑