This paper presents an end-to-end text-to-speech system with low latency on a
CPU, suitable for real-time applications. The system is composed of an
autoregressive attention-based sequence-to-sequence acoustic model and the
LPCNet vocoder for waveform generation. An acoustic model architecture that
adopts modules from both the Tacotron 1 and 2 models is proposed, while
stability is ensured by using a recently proposed purely location-based
attention mechanism, suitable for arbitrary sentence length generation. During
inference, the decoder is unrolled and acoustic feature generation is performed
in a streaming manner, allowing for a nearly constant latency which is
independent from the sentence length. Experimental results show that the
acoustic model can produce feature sequences with minimal latency about 31
times faster than real-time on a computer CPU and 6.5 times on a mobile CPU,
enabling it to meet the conditions required for real-time applications on both
devices. The full end-to-end system can generate almost natural quality speech,
which is verified by listening tests.

本文提出了一种针对实时应用具有低延迟的 CPU 端到端文本转语音系统，使用自回归基于注意力机制的序列到序列声学模型和 LPCNet 声码器进行波形生成，实验结果显示，该系统能够在 CPU 上几乎达到 31 倍的实时最小延迟，并且能够生成几乎自然的高质量语音。