Amazon Science·· 25d agoAI score58
Audible unveils controllable TTS pipeline for audiobook narration
Better speech synthesis for audiobooks
Summary
Audible's technology team described a controllable text-to-speech system for audiobooks that uses natural-language descriptions to direct dialogue delivery and keeps character voices consistent across a book. It combines a speech-captioning data pipeline with BookLLM, which identifies characters and their dialogue with 97% accuracy in English and 94% in Spanish. Dialogue differentiation improved by 3.7 points on a MUSHRA listening test.
This site provides summaries and links to the originals only.
Source: Amazon Science · amazon.science