Top Diff List Farm Source Search Help RSS Login



 HRI-JP Audition for Robots with Kyoto University (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 works 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.


HARK consists of a lot of modules for robot audition. These modules are implemented as a module for FlowDesigner and some modules are based on ManyEars. ManyEars provides microphone array processing to perform sound source localization, tracking, and separation.

  • Audio Signal Input
  • Sound Source Localization
  • Sound Source Separation
  • Acoustic Feature Extraction
  • Automatic Missing Feature Mask Generation
  • Speech Recognition Client

 Download and Installation

The Installation instruction for HARK is available here

 Related Work and Project

  • Dataflow-oriented GUI programming environment (middleware) Flowdesigner
  • Another robot audition project for Flowdesinger ManyEars
  • Open-Source Large Vocabulary CSR Engine Julius
  • Linux distribution Ubuntu
  • Advanced Linux Sound Architecture ALSA
  • Hidden Markov Toolkit HTK
  • The RESPITE CASA Toolkit Project CTK