Monotonic Alignment Search (MAS) (Kim et al., 2020), is a method to search for an alignment that maximizes the likelihood of data parameterized by a normalizing flow. ## References Kim, Jaehyeon, Sungwon Kim, Jungil Kong, and Sungroh Yoon. ‘Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search’. arXiv, 22 October 2020. [https://doi.org/10.48550/arXiv.2005.11129](https://doi.org/10.48550/arXiv.2005.11129).