Abstract
In this article, we introduce the state-of-the-art research outcomes of clinical applications of statistical speech synthesis and voice conversion techniques. In the speech information-processing field, there are emerging research topics and impressive research outcomes that may contribute to the quality of life of patients with vocal disabilities such as a technology to digitally mimick a voice of patients who are losing their voices due to diseases such as ALS (so the patients can use a personalized speech synthesizer that outputs their own voices) and a technology to digitally transform electrolaryngeal speech or disordered speech to natural-sounding intelligible speech in a real-time fashion. We also overview the current research topics after case studies with ALS patients and laryngectomees are described.
