论文标题
神经语音综合在浅滩上：提高LPCNET的效率
Neural Speech Synthesis on a Shoestring: Improving the Efficiency of LPCNet
论文作者
论文摘要
神经语音合成模型可以综合高质量的语音，但通常需要高度计算复杂性。在先前的工作中，我们引入了LPCNET，该LPCNET使用线性预测显着降低了神经合成的复杂性。在这项工作中，我们进一步提高了LPCNET的效率（针对算法和计算改进），以使其可在各种设备上使用。我们在运行速度快2.5倍时证明了合成质量的改善。由此产生的开源LPCNET算法可以在大多数现有手机上执行实时神经合成，甚至在某些嵌入式设备中也可以使用。
Neural speech synthesis models can synthesize high quality speech but typically require a high computational complexity to do so. In previous work, we introduced LPCNet, which uses linear prediction to significantly reduce the complexity of neural synthesis. In this work, we further improve the efficiency of LPCNet -- targeting both algorithmic and computational improvements -- to make it usable on a wide variety of devices. We demonstrate an improvement in synthesis quality while operating 2.5x faster. The resulting open-source LPCNet algorithm can perform real-time neural synthesis on most existing phones and is even usable in some embedded devices.
