Amazon Science develops new speech synthesis technology
The story so far
Audible's technology team has developed a new controllable speech synthesis technology to enhance the audiobook experience by combining large language models (LLMs) and three innovative technologies: developing a data synthesis pipeline to generate speech data with voice feature descriptions, training models to understand descriptions and generate matching audio; creating an automatic system to analyze book characters and identify dialogues, with an accuracy rate of 97%, providing stage directions for the model; in MUSHRA tests, the dialogue differentiation improved by 3.7 points, and in English and Spanish tests, 80% of the voice experience was significantly improved.
AI-written from the reports · Updated 26 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- Amazon ScienceBetter speech synthesis for audiobooks
Audible's technology team has developed a new controllable speech synthesis technology, by combining large language models (LLMs) and three innovative technologies to enhance the experience of audiobooks: 1) Develop a data synthesis pipeline to generate speech data with voice feature descriptions, train the model to understand the descriptions and generate matching audio; 2) Create an automatic system to analyze book characters and identify dialogues, with an accuracy of 97%, to provide stage directions for the model; 3) Improve the dialogue discrimination by 3.7 points in MUSHRA tests, and significantly improve the sound experience in English and Spanish tests by 80%.