Timezone: »
We introduce a technique for augmenting neural text-to-speech (TTS) with low-dimensional trainable speaker embeddings to generate different voices from a single model. As a starting point, we show improvements over the two state-of-the-art approaches for single-speaker neural TTS: Deep Voice 1 and Tacotron. We introduce Deep Voice 2, which is based on a similar pipeline with Deep Voice 1, but constructed with higher performance building blocks and demonstrates a significant audio quality improvement over Deep Voice 1. We improve Tacotron by introducing a post-processing neural vocoder, and demonstrate a significant audio quality improvement. We then demonstrate our technique for multi-speaker speech synthesis for both Deep Voice 2 and Tacotron on two multi-speaker TTS datasets. We show that a single neural TTS system can learn hundreds of unique voices from less than half an hour of data per speaker, while achieving high audio quality synthesis and preserving the speaker identities almost perfectly.
Author Information
Andrew Gibiansky (Baidu Research)
Sercan Arik (Baidu Research)
Gregory Diamos (Baidu SVAIL)
John Miller (Baidu Research)
Kainan Peng (Baidu Research)
Wei Ping (Baidu Research)
Jonathan Raiman (Baidu Research)
Yanqi Zhou (Baidu Research)
Related Events (a corresponding poster, oral, or spotlight)
-
2017 Spotlight: Deep Voice 2: Multi-Speaker Neural Text-to-Speech »
Wed. Dec 6th 01:40 -- 01:45 AM Room Hall A
More from the Same Authors
-
2021 Poster: Long-Short Transformer: Efficient Transformers for Language and Vision »
Chen Zhu · Wei Ping · Chaowei Xiao · Mohammad Shoeybi · Tom Goldstein · Anima Anandkumar · Bryan Catanzaro -
2018 Poster: Neural Voice Cloning with a Few Samples »
Sercan Arik · Jitong Chen · Kainan Peng · Wei Ping · Yanqi Zhou -
2018 Spotlight: Neural Voice Cloning with a Few Samples »
Sercan Arik · Jitong Chen · Kainan Peng · Wei Ping · Yanqi Zhou -
2017 : Scaling and Sparsity »
Gregory Diamos -
2017 : Future Hardware Directions »
Gregory Diamos · Jeff Dean · Simon Knowles · Michael James · Scott Gray