Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning
This work addresses the need for efficient and scalable TTS systems for applications requiring high-throughput synthesis, though it is incremental in improving upon existing neural methods.
The paper tackles the problem of scaling text-to-speech systems by introducing Deep Voice 3, a fully-convolutional attention-based neural TTS system that matches state-of-the-art naturalness while training ten times faster and scales to over 800 hours of audio from more than 2,000 speakers.
We present Deep Voice 3, a fully-convolutional attention-based neural text-to-speech (TTS) system. Deep Voice 3 matches state-of-the-art neural speech synthesis systems in naturalness while training ten times faster. We scale Deep Voice 3 to data set sizes unprecedented for TTS, training on more than eight hundred hours of audio from over two thousand speakers. In addition, we identify common error modes of attention-based speech synthesis networks, demonstrate how to mitigate them, and compare several different waveform synthesis methods. We also describe how to scale inference to ten million queries per day on one single-GPU server.