Speaker Conditional Wavernn: Towards Universal Neural Vocoder For Unseen Speaker And Recording Conditions
2020 · Dipjyoti Paul, Yannis Pantazis, Yannis Stylianou
Abstract
Recent advancements in deep learning led to human-level performance in single-speaker speech synthesis. However, there are still limitations in terms of speech quality when generalizing those systems into multiple-speaker models especially for unseen speakers and unseen recording qualities. For instance, conventional neural vocoders are adjusted to the training speaker and have poor generalization capabilities to unseen speakers. In this work, we propose a variant of WaveRNN, referred to as speaker conditional WaveRNN (SC-WaveRNN). We target towards the development of an efficient universal vocoder even for unseen speakers and recording conditions. In contrast to standard WaveRNN, SC-WaveRNN exploits additional information given in the form of speaker embeddings. Using publicly-available data for training, SC-WaveRNN achieves significantly better performance over baseline WaveRNN on both subjective and objective metrics. In MOS, SC-WaveRNN achieves an improvement of about 23% for seen
Authors
(none)
Tags
Stats
Related papers
- Towards Achieving Robust Universal Neural Vocoding (2018)0.00
- High-fidelity And Low-latency Universal Neural Vocoder Based On Multiband Wavernn With Data-driven Linear Prediction For Discrete Waveform Modeling (2021)6.77
- Speaker-adaptive Neural Vocoders For Parametric Speech Synthesis Systems (2018)2.26
- Wasserstein GAN And Waveform Loss-based Acoustic Model Training For Multi-speaker Text-to-speech Synthesis Systems Using A Wavenet Vocoder (2018)12.61
- Towards Robust Neural Vocoding For Speech Generation: A Survey (2019)0.00
- Rawnet: Advanced End-to-end Deep Neural Network Using Raw Waveforms For Text-independent Speaker Verification (2019)15.34
- Voice Conversion With Conditional Samplernn (2018)7.50
- Speaker Independence Of Neural Vocoders And Their Effect On Parametric Resynthesis Speech Enhancement (2019)6.34