Spoken Language Processing

Research tools and resources for Spoken Language Processing

Speech Synthesis for Lightweight Applications (SSLA) is a small framework designed for Text-to-Speech (TTS) synthesis. SSLA is only a speech synthesis back-end and it relies on the output of a Natural Language Processing (NLP) front-end for text processing and feature extraction. This demo is constructed using MLPLA as a front-end speech processing framework.

TTS Demo

You can download the SSLA runtime or browse our source code using the repository web view.