AdaSpeech: Adaptive Text to Speech for Custom Voice

By arXiv.org - 2021-03-05

Description

Custom voice, a specific text to speech (TTS) service in commercial speech platforms, aims to adapt a source TTS model to synthesize personal voice for a target speaker using few speech data. Custom v ...

Summary

  • Adaptive Text to Speech for Custom Voice Abstract: 1) to support diverse customers, the adaptation model needs to handle diverse acoustic conditions that could be very different from source speech data, and 2) to support a large number of customers, the adaptation parameters need to be small enough for each target speaker to reduce memory usage while maintaining high voice quality.
  • 2) To better trade off the adaptation parameters and voice quality, we introduce conditional layer normalization in the mel-spectrogram decoder of AdaSpeech, and fine-tune this part in addition to speaker embedding for adaptation.
  • arXiv is committed to these values and only works with partners that adhere to them.

 

Topics

  1. NLP (0.26)
  2. Backend (0.15)
  3. UX (0.11)

Similar Articles

How to put machine learning models into production

By Stack Overflow Blog - 2020-10-12

The goal of building a machine learning model is to solve a problem, and a machine learning model can only do so when it is in production and actively in use by consumers. As such, model deployment is ...