Timezone: »

Deep Voice 2: Multi-Speaker Neural Text-to-Speech
Andrew Gibiansky · Sercan Arik · Gregory Diamos · John Miller · Kainan Peng · Wei Ping · Jonathan Raiman · Yanqi Zhou

Tue Dec 05 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #78

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)

More from the Same Authors