Speech recognition & synthesis | Sri AI

Course overview

Voice is the whole premise of Sri AI. This course covers both directions: turning Sri Lankan speech into text, and producing speech people are willing to listen to.

Level: Advanced  ·  Mode: Part-time

Who this course is for

Engineers building voice interfaces for users who will not, and often cannot, type.

What you will learn

• Train and adapt ASR for Sri Lankan accents
• Build a TTS voice in Sinhala or Tamil
• Handle noise, dialect and code-switching
• Ship a voice interface that works on a low-end phone

Syllabus

1. Module 1: Audio and feature extraction
2. Module 2: Acoustic and language models
3. Module 3: Fine-tuning ASR on local speech
4. Module 4: Neural TTS and prosody
5. Module 5: Latency and on-device constraints

Final project

Every module ends in hands-on practice, and the course ends with a project you build and present. Your certificate names that project.

Before you start

Python for AI. Some signals background helps but is not required.