VoiceCode is an Open Source initiative started by the National Research Council of Canada, to develop a programming by voice toolbox. The aim of the project is to make programming through voice input as easy and productive as with mouse and keyboard. For install, Use subversion, as described in this page: http://sourceforge.net/apps/mediawiki/voicecode/index.php?title=VCode_1_Doc/InstallationManual.
IRC client for blind
A XFig based rapid prototype yeilding an audio speed alteration tool. This tool lets you arbitrarily alter the speed of audio files. It uses the WSOLA algorithm for audio speed alteration without pitch change.
This is an open source software. i need to convert a user speech who speaks in tamil and that should be processed and then it should be converted to tamil text in editor.
HMM-based singing voice synthesis system
Sinsy is an HMM-based singing voice synthesis system. This software is released under the Modified BSD license.
festival-ta synthesizes text in Tamil language into speech using Festival TTS. This is based on the festival-te project which provides supports for Telugu.
This project implements series of homework assignment from Columbia university course. The main target is to create a SIP enabled thin audio client for Linux.
gspeech is an open source voice dialing application for Qtopia green phone and other Linux or WindowsMobile based mobile devices.
Classic Game BreakOut. Started programming a couple days ago for fun! Still have to finish some issues. As well as finish the powerup's.
Record and playback sound with a slight (variable) delay. Implements the DAF principle as applied to speech therapy for stuttering/stammering.
A high quality Unified Subtitle parser for XBMC for external and embedded subtitles.
Make your mobile phone app conversationally-enabled. Users can speak to your app in multiple languages through an intelligent agent. Simple to use on Android.
A minimum voice generator. Maps text to sounds using also number to text (library included) transforms and spelling.
This is a WebTool to convert text to audio format content. This tool will allow users to post some text and take the output as mp3 file.
OpenVocoder is exactly what its name suggests: An open-source vocoder. OpenVocoder, or "OpVoc", is capable of encoding many different audio file formats, and applying a wide range of flexible filters to them, then exporting to one of many formats.
You`re sitting in a room with a lot of background voices and noise and doing an interview with someone while recording the conversation on tape or your MP3-Player. This software filters the voices wanted and improves their understandability.
Howe is a spoken dialogue system project designed for browsing instructions. The project serves as a base for research on new dialogue system capabilities.
Semiofon is a project that aims a semiotic based emotive speech syntesis for written and graphic information. It involves the development of different auxiliar softwares as parsers, sound annalysis and syntesis, and continuous media notation.
NLSML4J provides a Java API for working with Natural Language Semantics Markup Language (NLSML) results.
MRCP-TCK is a Technology Compatibility Kit (TCK) for the Media Resource Control Protocol version 2 (MRCPv2) specification providing a suite of tests that can be used to validate that a media server implementation complies with the MRCPv2 specification.
(rus) Civil Defence - цель проекта реализовать комплексное решение для организации библиотек для незрячих людей. (eng) Civil Defence - library for blind.
Speech ALIgnment (segmentAtioN) tool.
SRFSurvey is a Java application for doing telephone surveys using VoiceXML, and using the SpeakRight Framework for dynamic VoiceXML from Java. SRFSurvey is data-driven by an XML file that specifies the survey questions.
N Voice is a neural net based speech recognizer intented for letter recognition and writing it in file/window. Its intented to help people that can`t use the keybord (people without hands, arms or similar)
SIFS (Speech Intepretation and Feedback Shell) is a project to allow a user to be recognized by his or her voice, and have a program capable of calling them by their own name. Features will include command execution, Perl scripting interface, etc.