Janus Recognition Toolkit: Difference between revisions

Revision as of 09:25, 23 April 2012

Latest revision as of 06:21, 3 March 2025

(22 intermediate revisions by 14 users not shown)

Line 1:

{{Short description|General purpose speech recognition toolkit}}

'''Janus Recognition Toolkit''' ('''JRTk)'''), sometimes referred to as Janus, is a general purpose [[speech recognition]] toolkit developed and maintained by the Interactive Systems Laboratories at [[Carnegie Mellon University]] and [[Karlsruhe Institute of Technology]]. It is useful for both research and application development and is part of the JANUS speech-to-speech translation system.<ref>{{cite web |author=Sebastian Stüker |url=http://isl.ira.uka.de/english/1406.php |archive-url=https://web.archive.org/web/20120719091348/http://isl.ira.uka.de/english/1406.php |url-status=dead |archive-date=July 19, 2012 |title=KIT - Janus Recognition Toolkit |publisher=Isl.ira.uka.de |access-date=2012-04-23 }}</ref>

The JRTk provides a flexible Tcl/Tk script based environment which enables researchers to build state-of-the-art speech recognizers and allows them to develop, implement, and evaluate new methods. It implements an object oriented approach that unlike other toolkits is not a set of libraries and precompiled modules but a programmable shell with transparent, yet efficient objects.

Line 5 ⟶ 6:

Since version 5 JRTk features the IBIS decoder, a one-pass decoder that is based on a re-entrant single pronunciation prefix tree and makes use of the concept of linguistic context polymorphism. It is therefore able to incorporate full linguistic knowledge at an early stage. It is possible to decode in one pass, using the same engine in combination with a statistical n-gram language model as well as context- free grammars. It is also possible to use the decoder to rescore lattices in a very efficient way.

JRTk utilizes the concept of [[Hidden_Markov_model|Hidden Markov Models]] (HMMs) for acoustic modeling and offers many state-of-the-art techniques for acoustic pre-processing, acoustic model training, and speech decoding. Through its flexible, object oriented architecture it allows to configure all components in a very flexible way (e.g., pre-processing steps to execute, HMM topology, training sequence, algorithm parameters, adaptation sequences, etc.), without the need to modify source code or recompile.

JRTk has been used by the Interactive System Labs in many projects for speech recognition, such as:

* EU-BRIDGE <ref>{{cite web|author=Patricia Lichtblau |url=http://www.eu-bridge.eu |title=EU-Bridge - Homepage |publisher=Eu-bridge.eu |date=2012-02-01 |access-date=2012-04-23}}</ref>

* EVEIl-3D <ref>{{cite web|author=Esben Eidevik |url=http://www.eveil-3d.eu/ |title=EVEIL-3D-Startseite |publisher=Eveil-3d.eu |date=2012-04-15 |access-date=2012-04-23}}</ref>

* BABEL<ref>{{cite web|url=http://www.iarpa.gov/solicitations_babel.html |title=IARPA - Solicitations - Office of Incisive Analysis, Babel Program |publisher=Iarpa.gov |access-date=2012-04-23 |url-status=dead |archive-url=https://web.archive.org/web/20120422181014/http://www.iarpa.gov/solicitations_babel.html |archive-date=2012-04-22 }}</ref>

* BABEL <ref>http://www.iarpa.gov/solicitations_babel.html</ref>

* [[Quaero]]<ref>{{cite web|url=http://www.quaero.org |archive-url=https://web.archive.org/web/20010508153511/http://quaero.org/ |url-status=usurped |archive-date=May 8, 2001 |title=Bienvenue sur le site de Quaero |publisher=Quaero.org |access-date=2012-04-23}}</ref>

* Quaero <ref>http://www.quaero.org</ref>

* SFB 588 <ref>{{cite web|url=http://www.sfb588.uni-karlsruhe.de/about/ |title=SFB 588 - Humanoid Robots |publisher=Sfb588.uni-karlsruhe.de |access-date=2012-04-23}}</ref>

* TC-STAR <ref>{{cite web|url=http://cordis.europa.eu/projects/rcn/71389_en.html |title=European Commission : CORDIS : Projects & Results Service : Technology and corpora for speech to speech translation |website=Cordis.europa.eu |access-date=2016-07-16}}</ref>

* FAME <ref>{{cite web|url=http://cordis.europa.eu/projects/rcn/58337_en.html |title=European Commission : CORDIS : Projects & Results Service : Facilitating Agent in Multicultural Exchange |website=Cordis.europa.eu |access-date=2016-07-16}}</ref>

* [[Verbmobil]]

* NESPOLE! <ref>{{cite web|url=http://cordis.europa.eu/projects/rcn/55073_en.html |title=European Commission : CORDIS : Projects & Results Service : NEgotiating through SPOken Language in E-commerce |website=Cordis.europa.eu |access-date=2016-07-16}}</ref>

[[Category:Speech recognition]]

==References==

{{Reflist}}

[[Category:Speech recognition software]]