WomenTech_Event

Text To Speech

“OR”

Speech Synthesis

Thin Zar Phyo

Team Leader

Myanmar Text to Speech Project

[email protected]

Outline

• Introduction

Language

Language Processing

• Myanmar Text To Speech

Introduction

• speech and language were already

important parts of daily life before the

invention of the computer, the equipment

and technology

Language ?

• What is Language?

– Spoken + Written

• How many .. ?

• Human

• Animal

AI

• Natural Language Processing (NLP)

– Machine Translation

– Question and answering

– Expert System

• Image Processing

– OCR

– OMR

• Speech Processing

– TTS

– Voice Recg

• ….

NLP

Speech Processing

Image Processing

Text Processing

NLU

TTS or Speech Synthesis

NLP

+

Speech Processing/Technology

Digital Signal Processing Module (DSP)

•

Motivation

• Since speech is such a natural medium for

communication, users' expectations of a

speech application tend to be extremely

high.

• Not only for blind, but also when our hands

and eyes are busy –

• People use airline information system,

banking, ordering, reservation system

used at a hotel,

1st TTS System

• One of the first practical application of speech

synthesis was in 1936 when the U.K. Telephone

Company introduced a speaking clock.

• Speech synthesis as software or as an integral

part of the operating system was introduced in

the beginning of the 1980s on computers such

as Apple Macintosh.

• Myanmar Text To Speech

or

• Myanmar speech synthesizer

OR

• TTS Engine

TTS Synthesizer

• Generating natural sounding speech on

the fly, usually from text.

• A text to speech synthesizer is a computer

based system that should be able to read

any text.

• Speech should be intelligible and natural.

• Myanmar Text To Speech Synthesizer

Myanmar Text To Speech Engine Type License Copyright

1st

Version

31 May,2015 1st V Desktop Opensource IT Team, Myanmar

Christian Fellowship

of the Blind2nd Version 30

November,

2015

2nd V Web

Service

Opensource

Starting Date : 1st December, 2014

Technology & Platform

• Core Technologies

– C++

– Java

– .

• Platforms

– Ubuntu

– Window

Architecture

Basic Part of TTS1. Text Analysis

Normalization

2. Linguistic Analysis

G2P

3. Waveform generation

Waveform Analysis

Two Basic Strategies

• Dictionary based

• Rule-based

• Statistical

• Hybrid

• …

Current Situation

• Development

– Speech Synthesizer with The Festival

• Language Resources

– Myanmar Lexicon

– Speech Database

• Research

– Prosodic Analysis in Burmese

– Grapheme to Phoneme

Future

• Related work

– OCR

– MT

– …

• advances related fundamental

technologies such as

– multi-lingual speech translation

– multi-lingual speech transcription

– multi- lingual information retrieval

Conclusion

• The described speech synthesis system is

the open source.

• Contribution