Controllable neural text-to-speech synthesis using intuitive prosodic features
arXiv:2009.06775
Abstract
Modern neural text-to-speech (TTS) synthesis can generate speech that is indistinguishable from natural speech. However, the prosody of generated utterances often represents the average prosodic style of the database instead of having wide prosodic variation. Moreover, the generated prosody is solely defined by the input text, which does not allow for different styles for the same sentence. In this work, we train a sequence-to-sequence neural network conditioned on acoustic speech features to learn a latent prosody space with intuitive and meaningful dimensions. Experiments show that a model conditioned on sentence-wise pitch, pitch range, phone duration, energy, and spectral tilt can effectively control each prosodic dimension and generate a wide variety of speaking styles, while maintaining similar mean opinion score (4.23) to our Tacotron baseline (4.26).
Accepted for publication in Interspeech 2020
References in corpus (8)
- MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
- Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
- Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron
- Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions
- Efficient Neural Audio Synthesis
- CHiVE: Varying Prosody in Speech Synthesis with a Linguistically Driven Dynamic Hierarchical Conditional Variational Network
- Robust Sequence-to-Sequence Acoustic Modeling with Stepwise Monotonic Attention for Neural TTS
- Predicting Expressive Speaking Style From Text In End-To-End Speech Synthesis