Software Map

jAugment is a JINI-based, network-aware framework and set of initial applications for wearable computers and other computers with uncommon input/output-devices. It supports user interfaces from text-only to 3D.

SpeechLion is a speech recognition application for
desktop command and control. It is based on the
Sphinx-4 recognizer, and it allows the user to
control the Linux desktop using simple spoken
commands. Some example commands are "browse
google", "mouse click", "next window", "show
help", and "volume mute". SpeechLion recognizes
high-level commands for Web browsing via Firefox,
simple Emacs usage, window control, volume
control, and more. It also has low-level commands
for ad-hoc keyboard shortcuts and mouse actions.

The Snack sound extension adds commands for sound play/record and sound visualization, e.g. waveforms and spectrograms. It supports in- memory sound objects, file based audio, streaming audio, WAV, AU, AIFF, and MP3 file formats, synchronous and asynchronous playback. The visualization canvas item types update in real-time and can output postscript. New commands and file formats can be added using the Snack C-API.

FreeTTS is a speech synthesis system written entirely in Java. It is
based upon Flite, a small runtime speech synthesis engine developed
at Carnegie Mellon University. Flite is derived from the Festival
Speech Synthesis System from the University of Edinburgh and the
FestVox project from Carnegie Mellon University.

The SingIt Lyric Displayer is a program to display formatted lyrics, including tagged text, CD+G, and id3v2xx lyrics. It consists of several displayers, an integrated editor, query, and karaoke tools. It supports various players, such as XMMS, Noatun, and Rhythmbox.

SndBite is a specialized audio editor designed for breaking large recordings into smaller components with great efficiency. Its principal intended application is in linguistic research where it is often desirable to put each word or sentence into a separate file before further processing. It is also useful for measuring pause durations. Its features include multiple simultaneous views of the waveform at different resolutions, the ability to position window edges at transitions between sound and silence, automated setting of cut points at zero-crossings, automatic filename generation easily controlled by the user, and optional automatic playback on window motion. It is scriptable and may be run in batch mode without the GUI.

Real time communication software built to provide face-to-face advantages to remote gamers.

Julius is a high-performance large vocabulary
continuous speech recognition (LVCSR) engine for
speech-related research and development. You can
construct your own speech recognition system, but
you need a separate English acoustic model and
language model or grammar file.

GYach Enhanced is a feature-rich, improved version
of the original Gyach. It is the first Yahoo!
client for Linux with voice chat capabilities. It
offers almost all of the features you would expect
to find in the official Windows Yahoo! client. The
program offers support for chat, conferences,
buddy lists, and My Yahoo content. In addition,
Gyach Enhanced offers many features not available
in the official Yahoo! clients for Windows, Mac,
and Linux. Webcam support is under development and
planned for the future. Unlike the original Gyach,
GYach Enhanced is designed for Linux only.

speechd implements a /dev/speech device using either the Festival or rsynth speech synthesis packages. All plaintext written to this device will be spoken aloud (or optionally output as morse code if you are using the "morse" program as the underlying driver). Certain programs have been modified to make use of this device, including an ircII script called speech.irc, a Slashdot ticker called slashes and a package for TiK. All of these modified packages are available on the homepage.

LiarLiar is a computerized voice stress analysis
(CVSA) tool. Its main purpose is to detect stress
in a person's voice. Higher stress levels can be
an indication that the person is not being
truthful.

The Cainteoir Engine is a library for reading and recording different document formats (ePub, HTML, MHT, RTF, email, and others) to various audio output formats (such as PulseAudio, WAV, and Ogg/Vorbis). It also provides the following command-line tools: cainteoir, a front-end to the Cainteoir text-to-speech library; metadata, which extracts metadata from documents to RDF tuples; and tagcloud, which generates tag clouds and tag cloud data.

The freePBX (formerly Asterisk Management Portal)
project brings together best-of-breed applications
to produce a standardized implementation of
Asterisk, complete with Web-based administrative
interface.

Pause determines the location of silences in an
audio file for use in fragmentation of large
recordings, studies of pause duration, and the
like. It generates both a nicely formatted table
intended to be read by people and a simple
tab-delimited file that is easily parsed by software.

TranscriberAG は、音声信号の手動のアノテーションを支援するために設計されています。音声ラベリング、議事録の作成長い期間の音声の録音、セグメント化のための使いやすい GUI が、トピック変更と音響の条件を提供します。