Sample Efficient Adaptive Text-to-Speech

Yutian Chen (陈御天)

[0]

Yannis M. Assael

[0]

[0]

[0]

[0]

[0]

Luis C. Cobo

[0]

[0]

[0]

[0]

international conference on learning representations, 2019.

Cited by: 44|Views289

Keywords:

Mean Opinion Scoregradient descentmulti speakerspeech synthesisdeployment timeMore(12+)

Weibo:

These results are robust across speech datasets recorded under different conditions and, we demonstrate that the generated samples are capable of confusing the state-of-the-art text-independent speaker verification system

Abstract:

We present a meta-learning approach for adaptive text-to-speech (TTS) with few data. During training, we learn a multi-speaker model using a shared conditional WaveNet core and independent learned embeddings for each speaker. The aim of training is not to produce a neural network with fixed weights, which is then deployed as a TTS system....More

Code:

Data:

Full Text

View via Publisher