Home

Welcome To The VoiceBridge Wiki

VoiceBridge is an open source (AI-TOOLKIT Open Source License - Apache 2.0 based, very permissive and allows commercial use) speech recognition C++ toolkit optimized for MS Windows 64-bit (can be easily modified to compile on other operating systems). VoiceBridge fills the gap for MS Windows speech recognition developers.

VoiceBridge Official website: AI-TOOLKIT VoiceBridge

Discussion Group You may join the VoiceBridge & VoiceData discussion group and converse with your fellow developers and researchers here: VoiceBridge & VoiceData Discussion Group.

VoiceData: Automatic Speech Recognition (ASR) Data Generator Toolkit Visit also VoiceData on GitHub which can automatically generate audio and transcription files for ASR in several languages by only using text or even images e.g. imported from a scanner (you can scan a book or business papers with the text you desire). The voice recordings per sentence together with the aligned transcription text files can then be used to train an automatic speech recognition AI model. VoiceData also includes a built-in audio editor which can not only be used to edit, visualize and convert your audio files but also to transform the voice recordings. The audio editor can change the sample rate, the number of channels, can suppress noise, can cancel echo, change the tempo, change the rate, change the pitch frequency and it can also remove audio sections without human voice.

Contents

Home

Introduction & Getting Started Guide.

How To Report Bugs and Feature Requests.

How-To's.

Mfcc Configuration Options (mfcc.conf).

Gmm Mono Model Training Configuration Options (train.conf).

Delta + Delta-Delta Triphone Model Training Configuration Options (tri1.conf).

LDA+MLLT Model Training Configuration Options (tri2b.conf).

SAT Model Training Configuration Options (tri3b.conf).

Pitch Calculation Configuration Options (pitch.conf).

to be continued

You may also visit the VoiceBridge official website for more info: VoiceBridge website.