Honda Research Institute Japan Audition for Robots With Kyoto University
                   
聖徳太子

What is Hark?

HARK is open-sourced robot audition software consisting of sound source localization modules, sound source separation modules and automatic speech recognition modules of separated speech signals that work on any robot with any microphone configuration.


Since a robot with ears may be deployed to various auditory environments, the robot audition system should provide an easy way to adapt to them. HARK provides a set of modules to cope with various auditory environments by using an open-sourced middleware, FlowDesigner and reduces the overheads of data transfer between modules.


HARK has been open-sourced since April 2008. The resulting implementation of HARK with MUSIC-based sound source localization, GHDSS-based sound source separation and Missing-Feature-Theory-based automatic speech recognition (ASR) on several robots like HRP-2, SIG, SIG2, and Robovie R2 attains recognizing three simultaneous utterances in real time.

Let's Start HARK Download / Install

  • For Windwos Users
  • For Linux Users

News

August 20, 2019

第17回HARK講習会開催のお知らせ

参加募集案内はこちら

参加登録はこちら

June 24, 2019

HARK 3.0.7.1 released for Ubuntu.
See here for more detail.

June 07, 2019

HARK 3.0.7 released for Ubuntu.
See here for more detail.

May 29, 2019

HARK 3.0.6 released for Ubuntu.
See here for more detail.

March 25, 2019

HARK 3.0.5 updated for Ubuntu.
Updated KaldiDecoder for bugfix of the progress result output feature.

March 08, 2019

HARK 3.0.5 released for Ubuntu.
See here for more detail.

February 05, 2019

HARK 3.0.4 released for Ubuntu.
See here for more detail.

February 04, 2019

HARK Sample files for Optional Packages(HARK-Binaural+, HARK-Music and HARK-Rescue) are released (Version 3.x or later)

January 31, 2019

HARK 3.0.3 released for Ubuntu. (HARK-Binaural+, HARK-Music and HARK-ENE included)
See here for more detail.

January 11, 2019

HARK 3.0.2.1 released for Windows.
See here for more detail.

MORE

Back to Top