Santiago Pascual1, Antonio Bonafonte1, Joan Serrà2
1Universitat Politècnica de Catalunya, Barcelona, Spain
2Telefónica Research, Barcelona, Spain
This is a sample page of our work on Self-Attention Linguistic-Acoustic Decoder. In this work we build an alternative acoustic mapping model to that of previous two-stage deep learning systems, implemented in our open source TTS framework MUSA.