Speech-to-Singing Conversion in an Encoder-Decoder Framework
arXiv:2002.06595
Abstract
In this paper our goal is to convert a set of spoken lines into sung ones. Unlike previous signal processing based methods, we take a learning based approach to the problem. This allows us to automatically model various aspects of this transformation, thus overcoming dependence on specific inputs such as high quality singing templates or phoneme-score synchronization information. Specifically, we propose an encoder--decoder framework for our task. Given time-frequency representations of speech and a target melody contour, we learn encodings that enable us to synthesize singing that preserves the linguistic content and timbre of the speaker while adhering to the target melody. We also propose a multi-task learning based objective to improve lyric intelligibility. We present a quantitative and qualitative analysis of our framework.
arXiv commentAccepted at IEEE ICASSP 2020
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Instance Normalization: The Missing Ingredient for Fast Stylization
- Tacotron: Towards End-to-End Speech Synthesis
- Efficient Neural Audio Synthesis
- Audio style transfer
- A Universal Music Translation Network
- Score and Lyrics-Free Singing Voice Generation
- Singing Style Transfer Using Cycle-Consistent Boundary Equilibrium Generative Adversarial Networks