Sequence-to-sequence singing synthesis using the feed-forward transformer
Sequence-to-sequence singing synthesis using the feed-forward transformer
Citació
- Blaauw M, Bonada J. Sequence-to-sequence singing synthesis using the feed-forward transformer. In: 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP); 2020 May 4-8; Barcelona, Spain. New Jersery: The Institute of Electrical and Electronics Engineers; 2020. p. 7229-33. DOI: 10.1109/ICASSP40776.2020.9053944
Enllaç permanent
Descripció
Resum
We propose a sequence-to-sequence singing synthesizer, which avoids the need for training data with pre-aligned phonetic and acoustic features. Rather than the more common approach of a content-based attention mechanism combined with an autoregressive decoder, we use a different mechanism suitable for feed-forward synthesis. Given that phonetic timings in singing are highly constrained by the musical score, we derive an approximate initial alignment with the help of a simple duration model. Then, using a decoder based on a feed-forward variant of the Transformer model, a series of self-attention and convolutional layers refines the result of the initial alignment to reach the target acoustic features. Advantages of this approach include faster inference and avoiding the exposure bias issues that affect autoregressive models trained by teacher forcing. We evaluate the effectiveness of this model compared to an autoregressive baseline, the importance of self-attention, and the importance of the accuracy of the duration model.Descripció
Comunicació presentada a: ICASSP 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, celebrat en línia del 4 al 8 de maig de 2020.