Saxe: Text-to-Speech Synthesis Engine Applicable to Diverse Use Cases

Abstract

Technology overview High-accuracy reading of heteronyms accord-ing to context Speech synthesis can be broadly divided into a textanalysis section that infers the reading and accents of characters from input text and a speech-synthesis section that generates synthesized speech from the

Researching AI Technologies to Support and Substitute Human Activities

“…Next is "Saxe: Text-to-Speech Synthesis Engine Applicable to Diverse Use Cases" [8]. Regarding speech-synthesis technology for generating speech for virtual announcers, AI agents, etc., this article introduces technology for high-accuracy reading of heteronyms according to context and deep-neuralnetwork speech-synthesis technology for reproducing a variety of speaker characteristics at low cost.…”