Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence LearningDownload PDF

15 Feb 2018 (modified: 07 Apr 2024)ICLR 2018 Conference Blind SubmissionReaders: Everyone
Abstract: 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 an order of magnitude faster. We scale Deep Voice 3 to dataset 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 a single GPU server.
Keywords: 2000-Speaker Neural TTS, Monotonic Attention, Speech Synthesis
Code: [![Papers with Code](/images/pwc_icon.svg) 7 community implementations](https://paperswithcode.com/paper/?openreview=HJtEm4p6Z)
Data: [LibriSpeech](https://paperswithcode.com/dataset/librispeech)
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 4 code implementations](https://www.catalyzex.com/paper/arxiv:1710.07654/code)
8 Replies

Loading